Search

Deepfakes represent a class of synthetic media crafted with the aid of advanced deep learning techniques that exhibit an unparalleled degree of authenticity. The rapid advancement in Artificial Intelligence (AI) has contributed to an increase in the prevalence of deepfakes on the internet, consequently amplifying the spread of misinformation among the public. Consequently, the detection of deepfakes has become a pressing concern. In this context, we put forth a comprehensive framework for deepfake video detection, which is built upon three distinct layers. The first layer, termed as the RGB features extraction layer, is designed to identify potential signs of forgery within the spatial domain of analogous video frames. The second layer, known as the GAN features extraction layer, focuses on the extraction of forgery fingerprints in the high-frequency region. This layer is specifically engineered to detect the fingerprints left by the Generative Adversarial Network (GAN) process in fake videos and the traces of the imaging process in genuine videos. The third and final layer, referred to as the facial region intra-frame inconsistency feature extraction layer, is dedicated to uncovering the anomalies associated with the manipulation process. This is achieved by extracting features from both the inner and outer regions of the manipulated portion of a frame. The extensive experimental evaluations have underscored the superior performance of proposed approach in comparison to existing state-of-the-art methods. [ABSTRACT FROM AUTHOR]

To address the issues of target feature blurring and increased false detections caused by high compression rates in deepfake videos, as well as the high computational resource requirements of existing face extractors, we propose a lightweight face extractor to assist deepfake detection, GCS-YOLOv8. Firstly, we employ the HGStem module for initial downsampling to address the issue of false detections of small non-face objects in deepfake videos, thereby improving detection accuracy. Secondly, we introduce the C2f-GDConv module to mitigate the low-FLOPs pitfall while reducing the model's parameters, thereby lightening the network. Additionally, we add a new P6 large target detection layer to expand the receptive field and capture multi-scale features, solving the problem of detecting large-scale faces in low-compression deepfake videos. We also design a cross-scale feature fusion module called CCFG (CNN-based Cross-Scale Feature Fusion with GDConv), which integrates features from different scales to enhance the model's adaptability to scale variations while reducing network parameters, addressing the high computational resource requirements of traditional face extractors. Furthermore, we improve the detection head by utilizing group normalization and shared convolution, simplifying the process of face detection while maintaining detection performance. The training dataset was also refined by removing low-accuracy and low-resolution labels, which reduced the false detection rate. Experimental results demonstrate that, compared to YOLOv8, this face extractor achieves the AP of 0.942, 0.927, and 0.812 on the WiderFace dataset's Easy, Medium, and Hard subsets, representing improvements of 1.1%, 1.3%, and 3.7% respectively. The model's parameters and FLOPs are only 1.68 MB and 3.5 G, reflecting reductions of 44.2% and 56.8%, making it more effective and lightweight in extracting faces from deepfake videos. [ABSTRACT FROM AUTHOR]

The widespread dissemination of Deepfake in social networks has posed serious security risks, thus necessitating the development of an effective Deepfake detection technique. Currently, video-based detectors have not been explored as extensively as image-based detectors. Most existing video-based methods only consider temporal features without combining spatial features, and do not mine deeper-level subtle forgeries, resulting in limited detection performance. In this paper, a novel spatiotemporal trident network (STN) is proposed to detect both spatial and temporal inconsistencies of Deepfake videos. Since there is a large amount of redundant information in Deepfake video frames, we introduce convolutional block attention module (CBAM) on the basis of the I3D network and optimize the structure to make the network better focus on the meaningful information of the input video. Aiming at the defects in the deeper-level subtle forgeries, we designed three feature extraction modules (FEMs) of RGB, optical flow, and noise to further extract deeper video frame information. Extensive experiments on several well-known datasets demonstrate that our method has promising performance, surpassing several state-of-the-art Deepfake video detection methods. [ABSTRACT FROM AUTHOR]

The capacity to create "fake" videos has recently raised concerns about the reliability of multimedia content. Identifying between true and false information is a critical step toward resolving this problem. On this issue, several algorithms utilizing deep learning and facial landmarks have yielded intriguing results. Facial landmarks are traits that are solely tied to the subject's head posture. Based on this observation, we study how Head Pose Estimation (HPE) patterns may be utilized to detect deepfakes in this work. The HPE patterns studied are based on FSA-Net, SynergyNet, and WSM, which are among the most performant approaches on the state-of-the-art. Finally, using a machine learning technique based on K-Nearest Neighbor and Dynamic Time Warping, their temporal patterns are categorized as authentic or false. We also offer a set of experiments for examining the feasibility of using deep learning techniques on such patterns. The findings reveal that the ability to recognize a deepfake video utilizing an HPE pattern is dependent on the HPE methodology. On the contrary, performance is less dependent on the performance of the utilized HPE technique. Experiments are carried out on the FaceForensics++ dataset that presents both identity swap and expression swap examples. The findings show that FSA-Net is an effective feature extraction method for determining whether a pattern belongs to a deepfake or not. The approach is also robust in comparison to deepfake videos created using various methods or for different goals. In the mean the method obtain 86% of accuracy on the identity swap task and 86.5% of accuracy on the expression swap. These findings offer up various possibilities and future directions for solving the deepfake detection problem using specialized HPE approaches, which are also known to be fast and reliable. [ABSTRACT FROM AUTHOR]

Video deepfake detection has emerged as a critical field within the broader domain of digital technologies driven by the rapid proliferation of AI-generated media and the increasing threat of its misuse for deception and misinformation. The integration of Convolutional Neural Network (CNN) with Long Short-Term Memory (LSTM) has proven to be a promising approach for improving video deepfake detection, achieving near-perfect accuracy. CNNs enable the effective extraction of spatial features from video frames, such as facial textures and lighting, while LSTM analyses temporal patterns, detecting inconsistencies over time. This hybrid model enhances the ability to detect deepfakes by combining spatial and temporal analysis. However, the existing research lacks systematic evaluations that comprehensively assess their effectiveness and optimal configurations. Therefore, this paper provides a comprehensive review of video deepfake detection techniques utilising hybrid CNN-LSTM models. It systematically investigates state-of-the-art techniques, highlighting common feature extraction approaches and widely used datasets for training and testing. This paper also evaluates model performance across different datasets, identifies key factors influencing detection accuracy, and explores how CNN-LSTM models can be optimised. It also compares CNN-LSTM models with non-LSTM approaches, addresses implementation challenges, and proposes solutions for them. Lastly, open issues and future research directions of video deepfake detection using CNN-LSTM will be discussed. This paper provides valuable insights for researchers and cyber security professionals by reviewing CNN-LSTM models for video deepfake detection contributing to the advancement of robust and effective deepfake detection systems. [ABSTRACT FROM AUTHOR]

Manipulated media – images, video, and audio – have proliferated online. Widely available modification software, rudimentary practices, and advanced techniques involving machine learning and artificial intelligence have been used to manipulate media. This article critically explores illegal and nonconsensual nude and sexually explicit (NSE) deepfakes and the measures implemented to counter them. The motivating questions for this analysis are: What measures are in place to counter illegal and nonconsensual NSE deepfakes? Are these measures sufficient? The objectives of this article are three-fold: (1) to identify illegal and nonconsensual NSE deepfakes and illegal uses of them; (2) to critically evaluate the current legal and technological countermeasures available in various jurisdictions to combat illicit and nonconsensual NSE deepfakes; and (3) to make recommendations based on challenges and deficits in existing legal and technological mechanisms employed to tackle them. Ultimately, our findings indicate that there are technologies and legal measures that could effectively reduce the harm experienced by victims if: there is a collective will from the corporate, legislative, and political spheres to effectively execute these changes; and legal liability to remove NSE deepfakes is placed on the online platforms and websites that host and distribute this content. [ABSTRACT FROM AUTHOR]

Automatic Speaker Verification (ASV) systems are crucial in various fields, enabling speaker identification for authentication, fraud detection, and forensic applications. While the simplicity and effectiveness of speech biometrics are driving the demand for ASV systems, their increasing popularity raises concerns about vulnerability to speech attacks. To enhance the security of these systems, the work in this paper proposes a spectrogram-based solution that leverages the robustness of spectrograms in audio analysis and feature extraction. The proposed model consists of two main components: frontend and backend. In the frontend, it introduces a novel spectrogram MelCochleaGram (MCG) by fusing Mel Spectrogram and Cochleagram, sequentially. For the backend implementation, pre-trained deep learning models, including ResNet50, ResNet50V2, and InceptionV3, are employed using the Keras framework. These models are individually paired with MCG to detect deepfake and replay attacks. To validate the effectiveness of the proposed system, thorough experimentation is conducted on two datasets: the DEepfake CROss-lingual (DECRO) evaluation dataset and the Voice Spoofing Detection Corpus (VSDC). The proposed combination of MCG with ResNet50 has achieved an Equal Error Rate (EER) of 0.2%, and 1.2% for deepfake detection over DECRO English and Chinese datasets, respectively. Also, for replay attack detection, the proposed combination has produced an EER of 1.4%. [ABSTRACT FROM AUTHOR]

Rapid innovations in media technologies have ushered in diverse entertainment avenues, including politically oriented content, presenting both novel opportunities and societal challenges. This study delves into the implications of the burgeoning deepfake phenomenon, particularly focusing on audience interpretation and engagement with deepfake parodies, a quintessential example of "misinfotainment." Additionally, it examines the potential impact of artificial intelligence (AI) disclaimers on audience understanding and related consequences. To probe this, two experiments (N  =   2,808) were executed featuring parodied politicians adopting opposing viewpoints on the issue of climate change. U.S. participants were either exposed to deepfake videos prefaced with AI disclaimers or without. Results indicate that the inclusion of an AI disclaimer significantly influenced audience comprehension and their ability to recognize the parody. These factors were subsequently associated with enjoyment, discounting, and counterarguing, which in turn showed different relationships with policy support and sharing intentions. This article culminates with insights into the theoretical underpinnings and practical ramifications of these findings. [ABSTRACT FROM AUTHOR]

In the ecosystem of artificial intelligence (AI), generative models enable the creation of hyper-realistic manipulations that are extremely plausible due to the precision of the audiovisual objects. These deepfakes are undetectable thanks to their components, which heightens concerns about the distortion of reality in the information ecosystem and how the ability to distinguish between real and fake audiovisual content affects public trust and democratic systems. This is a major challenge for media and information literacy if it is to combat misinformation effectively. In this context, this study presents the results of a quasi-experiment conducted with 80 young people from the Community of Madrid (Spain) to assess their ability to detect deepfakes in immersive environments and to establish whether the context-identifying elements that enable detection of the reputation of the media source shape the credibility of the images. The results show that the images take precedence over the context identifiers, preventing a critical reading of the information that would make it possible to detect visual forgeries, something that is reinforced by their exceptional verisimilitude. It is concluded that the new post-humanist biome of virtual reality and artificial intelligence requires a reorientation of media and information literacy to raise the public's awareness and educate them to make them less susceptible to disinformation based on deepfakes created with generative models. [ABSTRACT FROM AUTHOR]

Video recordings accurately capture facial expression movements; however, they are difficult for face perception researchers to standardise and manipulate. For this reason, dynamic morphs of photographs are often used, despite their lack of naturalistic facial motion. This study aimed to investigate how humans perceive emotions from faces using real videos and two different approaches to artificially generating dynamic expressions – dynamic morphs, and AI-synthesised deepfakes. Our participants perceived dynamic morphed expressions as less intense when compared with videos (all emotions) and deepfakes (fearful, happy, sad). Videos and deepfakes were perceived similarly. Additionally, they perceived morphed happiness and sadness, but not morphed anger or fear, as less genuine than other formats. Our findings support previous research indicating that social responses to morphed emotions are not representative of those to video recordings. The findings also suggest that deepfakes may offer a more suitable standardized stimulus type compared to morphs. Additionally, qualitative data were collected from participants and analysed using ChatGPT, a large language model. ChatGPT successfully identified themes in the data consistent with those identified by an independent human researcher. According to this analysis, our participants perceived dynamic morphs as less natural compared with videos and deepfakes. That participants perceived deepfakes and videos similarly suggests that deepfakes effectively replicate natural facial movements, making them a promising alternative for face perception research. The study contributes to the growing body of research exploring the usefulness of generative artificial intelligence for advancing the study of human perception. [ABSTRACT FROM AUTHOR]

Deepfake images are combined media constructed from deep learning (DL) methods, usually Generative Adversarial Networks (GANs), to manipulate visual content, often giving rise to convincing and fabricating descriptions of scenes or people. The Bayesian machine learning (ML) model has made crucial strides over the past two decades, illustrating promise in diverse applications. In deepfake images, detection utilizes computer vision (CV) and ML to spot manipulated content by analyzing unique artefacts and patterns. Recent techniques utilize DL to train neural networks to discriminate between real and fake images, improving the fight against digital manipulation and preserving media integrity. These systems can efficiently detect subtle inconsistencies or anomalies specific to deepfake creations by learning from large datasets of both real and deepfake images. This enables the mitigation of fraudulent content and reliable detection in digital media. We introduce a new Coronavirus Herd Immunity Optimizer with a Deep Learning-based Deepfake Image Detection and Classification (CHIODL-DIDC) technique. The CHIODL-DIDC technique aimed to detect and classify the existence of fake images. To accomplish this, the CHIODL-DIDC technique initially used a median filtering (MF) based image filtering approach. Besides, the CHIODL-DIDC technique utilized the MobileNetv2 model for extracting feature vectors. Moreover, the hyperparameter tuning of the MobileNetv2 model was accomplished using the CHIO method. For deepfake image detection, the CHIODL-DIDC technique implements the deep belief network (DBN) model. Finally, the Bayesian optimization algorithm (BOA) was utilized to select the effectual hyperparameter of the DBN model. The CHIODL-DIDC method's empirical analysis was examined using a benchmark fake image dataset. The performance validation of the CHIODL-DIDC technique illustrated a superior accuracy value of 98.16% over other models under A c c u y , P r e c n , R e c a l , F S c o r e , and MCC metrics. [ABSTRACT FROM AUTHOR]

Artificial images and recordings are broad on the web via different media channels such as blogs, YouTube videos, etc. These manipulated and synthesized images tend to steal the identity of individuals and majorly contribute to establishing societal disruptions such as theft, political errors, social engineering, disinformation attacks and reputation fraud. These fake visual objects gradually came to be known as deep fakes. Different deep learning techniques are used to generate deepfake images which go unnoticed by human eyes. It is essential to develop a defense mechanism that can stop the common people from being manipulated and harnessed. The objective of this work is to develop an ensemble deep learning-based system that can differentiate between fake and real images. With the use of the recommended optical flow technique, a novel approach is proposed that extracts the apparent motion of image pixels which gives more accurate results compared to other state-of-the-art. FaceForensics + + dataset is used to test the extraction algorithms and ensemble model which fetched an accuracy of 86.02% for the DeepFake subset and 85.7% for the FaceSwap subset of the dataset. To the best knowledge, no one has completely used the ensemble model- OptiFake on the optical flow derived frames, highlighting a research gap in the field of deepfake detection. [ABSTRACT FROM AUTHOR]

Among its many applications, artificial intelligence (AI) can be used to manipulate audiovisual content for malicious intents. Such manipulations – which are commonly known as deepfakes – present a significant obstacle to maintaining truth in sectors that serve the public interest, and it is necessary to take proactive fact-checking actions to respond to the threat they pose. The current study conducted an online experiment focusing on the topic of cancer prevention. In this experiment, we further examined the influence of individual differences, such as issue relevance and motns, in health information consumption. When compared to textual disinformation, health-related audiovisual deepfakes were found to have a significant effect on increasing misperceptions but no such effect on fact-checking intentions. We also found that exposure to such deepfakes discouraged individuals with high issue relevance from engaging in fact-checking. Deepfakes were also shown to have a particularly potent effect on increasing misperceptions among individuals with high (illusory) accuracy motivations. These findings underscore the need for increased awareness regarding the detrimental effects of health deepfakes in particular and the urgent importance of further elucidating individual variations to ultimately develop more comprehensive approaches to combat deepfakes. [ABSTRACT FROM AUTHOR]

One of today's most important developments and innovations brought by digital technologies is artificial intelligence-based deepfake applications. Deepfake is explained as the technology of automatically changing the faces of people in images with the use of deep learningbased algorithms. Deepfake, which is built on visual manipulation and editing, stands out as the core concept of this research. This research paper provides an overview of what deepfake applications are, their wide range of uses, their advantages (their use in areas such as education, healthcare, entertainment sector, arts) and their possible disadvantages (manipulative illegal uses). In this context, the commercial of the Russian operator company Megafon was selected as the sample. Each frame of the commercial was examined and analyzed with the semiotic method. The commercial film, which was created with Deepfake technology, was analyzed within the scope of plain meaning / connotation, and the messages intended to be given to the audience were analyzed and explained. The technical analysis of the image of the digital twin of the famous actor (Bruce Willis) in the commercial film created with deepfake was made. The effects of the advertisement shot with deepfake technology on the visual narrative compared to traditional methods were analyzed. [ABSTRACT FROM AUTHOR]

In an era where all information can be reached with one click and by using the internet, the risk has increased in a significant manner. Deepfakes are one of the main threats on the internet, and affect society by influencing and altering information, decisions, and actions. The rise of artificial intelligence (AI) has simplified the creation of deepfakes, allowing even novice users to generate false information in order to create propaganda. One of the most prevalent methods of falsification involves images, as they constitute the most impactful element with which a reader engages. The second most common method pertains to videos, which viewers often interact with. Two major events led to an increase in the number of deepfake images on the internet, namely the COVID-19 pandemic and the Russia–Ukraine conflict. Together with the ongoing "revolution" in AI, deepfake information has expanded at the fastest rate, impacting each of us. In order to reduce the risk of misinformation, users must be aware of the deepfake phenomenon they are exposed to. This also means encouraging users to more thoroughly consider the sources from which they obtain information, leading to a culture of caution regarding any new information they receive. The purpose of the analysis is to extract the most relevant articles related to the deepfake domain. Using specific keywords, a database was extracted from Clarivate Analytics' Web of Science Core Collection. Given the significant annual growth rate of 161.38% and the relatively brief period between 2018 and 2023, the research community demonstrated keen interest in the issue of deepfakes, positioning it as one of the most forward-looking subjects in technology. This analysis aims to identify key authors, examine collaborative efforts among them, explore the primary topics under scrutiny, and highlight major keywords, bigrams, or trigrams utilized. Additionally, this document outlines potential strategies to combat the proliferation of deepfakes in order to preserve information trust. [ABSTRACT FROM AUTHOR]

With the development of artificial intelligence (AI), deepfakes, in which the face of one person is changed to another expression of the same person or a different person, have advanced. There is a need for countermeasures against crimes that exploit deepfakes. Methods to interfere with deepfake generation by adding an invisible weak adversarial signal to an image have been proposed. However, there is a problem: the weak signal can be easily removed by processing the image. In this paper, we propose trap signals that appear in response to a process that weakens adversarial signals. We also propose a new type of adversarial signal injection that allow us to reconstruct and change the original image as far as people do not feel strange by Denoising Diffusion Probabilistic Model (DDPM)-based Iterative Latent Variable Refinement. In our experiments with Star Generative Adversarial Network (StarGAN) trained with the CelebFaces Attributes (CelebA) Dataset, we demonstrate that the proposed approach achieves more robust proactive deepfake defense. [ABSTRACT FROM AUTHOR]

Civil disorder has always plagued humanity, with violence being triggered by real or perceived grievances, rumours and speculation, and internal or external agitators. The risk to people, communities, businesses and the rule of law is not isolated to a particular country or society. The propensity for violence and how it is incited is, however, an evolving threat with the advent of the 'modern riot'. The causes of violence centre on economic and social injustice, sports- and event-related riots, a reaction to police or security forces and political unrest. As the US nears the contentious 2024 elections, the failing trust in the three branches of government combined with external global tensions and conflict, threats from domestic extremist groups, a rising acceptance of violence as a means of settling political disagreements, hostile nation actors and international terror groups that exploit societal instability create fertile conditions for widespread violence. Exacerbating these factors are the risks from artificial intelligence (AI) deepfake, rapid mass communications, the citizen journalist, prominent influencers amplifying grievances and inflammatory media reporting. This convergence of exacerbators and accelerants for political discord offers the potential for serious security risks and significant business disruption. [ABSTRACT FROM AUTHOR]

Recent advancements in generative artificial intelligence (AI) have raised concerns about its potential to create convincing fake social media accounts, but empirical evidence is lacking. In this paper, we present a systematic analysis of Twitter (X) accounts using human faces generated by Generative Adversarial Networks (GANs) for their profile pictures. We present a dataset of 1,420 such accounts and show that they are used to spread scams, disseminate spam, and amplify coordinated messages, among other inauthentic activities. Leveraging a feature of GAN-generated faces--consistent eye placement--and supplementing it with human annotation, we devise an effective method for identifying GAN-generated profiles in the wild. Applying this method to a random sample of active Twitter users, we estimate a lower bound for the prevalence of profiles using GAN-generated faces between 0.021% and 0.044%--around 10,000 daily active accounts. These findings underscore the emerging threats posed by multimodal generative AI. We release the source code of our detection method and the data we collect to facilitate further investigation. Additionally, we provide practical heuristics to assist social media users in recognizing such accounts. [ABSTRACT FROM AUTHOR]

Synthetic images ar---e created using computer graphics modeling and artificial intelligence techniques, referred to as deepfakes. They modify human features by using generative models and deep learning algorithms, posing risks violations of social media regulations and spread false information. To address these concerns, the study proposed an improved generative adversarial network (GAN) model which improves accuracy while differentiating between real and fake images focusing on data augmentation and label smoothing strategies for GAN training. The study utilizes a dataset containing human faces and employs DCGAN (deep convolutional generative adversarial network) as the base model. In comparison with the traditional GANs, the proposed GAN outperform in terms of frequently used metrics i.e., Fréchet Inception Distance (FID) and accuracy. The model effectiveness is demonstrated through evaluation on the Flickr-Faces Nvidia dataset and Fakefaces d--ataset, achieving an FID score of 55.67, an accuracy of 98.82%, and an F1-score of 0.99 in detection. This study optimizes the model parameters to achieve optimal parameter settings. This study fine-tune the model parameters to reach optimal settings, thereby reducing risks in synthetic image generation. The article introduces an effective framework for both image manipulation and detection. [ABSTRACT FROM AUTHOR]

Deepfake images have become a major problem in today’s digital landscape. Such images are usually created using advanced machine learning techniques. These fake images can deceive viewers, posing risks to privacy, security, and trust. In this paper we introduce an innovative approach to detect deepfake by analyzing facial landmarks and computing corresponding expert features, train multiple classifier models based on three sets of features and achieve an accuracy of 0.682 and F1-score of 0.680. Using the coefficients of the resulting models, we evaluate the importance of features and identify the most important ones.

Deepfake images are combined media constructed from deep learning (DL) methods, usually Generative Adversarial Networks (GANs), to manipulate visual content, often giving rise to convincing and fabricating descriptions of scenes or people. The Bayesian machine learning (ML) model has made crucial strides over the past two decades, illustrating promise in diverse applications. In deepfake images, detection utilizes computer vision (CV) and ML to spot manipulated content by analyzing unique artefacts and patterns. Recent techniques utilize DL to train neural networks to discriminate between real and fake images, improving the fight against digital manipulation and preserving media integrity. These systems can efficiently detect subtle inconsistencies or anomalies specific to deepfake creations by learning from large datasets of both real and deepfake images. This enables the mitigation of fraudulent content and reliable detection in digital media. We introduce a new Coronavirus Herd Immunity Optimizer with a Deep Learning-based Deepfake Image Detection and Classification (CHIODL-DIDC) technique. The CHIODL-DIDC technique aimed to detect and classify the existence of fake images. To accomplish this, the CHIODL-DIDC technique initially used a median filtering (MF) based image filtering approach. Besides, the CHIODL-DIDC technique utilized the MobileNetv2 model for extracting feature vectors. Moreover, the hyperparameter tuning of the MobileNetv2 model was accomplished using the CHIO method. For deepfake image detection, the CHIODL-DIDC technique implements the deep belief network (DBN) model. Finally, the Bayesian optimization algorithm (BOA) was utilized to select the effectual hyperparameter of the DBN model. The CHIODL-DIDC method's empirical analysis was examined using a benchmark fake image dataset. The performance validation of the CHIODL-DIDC technique illustrated a superior accuracy value of 98.16% over other models under $ Acc{u}_{y} $ , $ Pre{c}_{n} $ , $ Rec{a}_{l} $ , $ {F}_{Score} $ , and MCC metrics.

Abstract Manipulated media – images, video, and audio – have proliferated online. Widely available modification software, rudimentary practices, and advanced techniques involving machine learning and artificial intelligence have been used to manipulate media. This article critically explores illegal and nonconsensual nude and sexually explicit (NSE) deepfakes and the measures implemented to counter them. The motivating questions for this analysis are: What measures are in place to counter illegal and nonconsensual NSE deepfakes? Are these measures sufficient? The objectives of this article are three-fold: (1) to identify illegal and nonconsensual NSE deepfakes and illegal uses of them; (2) to critically evaluate the current legal and technological countermeasures available in various jurisdictions to combat illicit and nonconsensual NSE deepfakes; and (3) to make recommendations based on challenges and deficits in existing legal and technological mechanisms employed to tackle them. Ultimately, our findings indicate that there are technologies and legal measures that could effectively reduce the harm experienced by victims if: there is a collective will from the corporate, legislative, and political spheres to effectively execute these changes; and legal liability to remove NSE deepfakes is placed on the online platforms and websites that host and distribute this content.

In the digital society of "open sharing of information and interconnection of everything", the information traces characterized with "massive, multi-source and explosive growth" in the internet provide rich "mineral deposits" for open-source intelligence collecting. Intelligence processing enabled by advanced artificial intelligence technologies, such as natural language processing and computer vision, greatly improves the efficiency of intelligence production and is widely used in the field of security. However, generative artificial intelligence represented by deepfake has opened the "Pandora's box" of artificial intelligence and is used to create digital wildfires and put false information, which confuse the public and bring crucial challenges to the integration of intelligent intelligence. This paper focuses on open-source intelligence and deeply analyzes its characteristics and existing challenges. Then, this paper summarizes the development of advanced artificial intelligence technology in opensource intelligence fusion, summarizes the existing intelligence spoofing attack methods and intelligence anti-spoofing defense methods from the perspective of confrontation. Finally, new directions of intelligence fusion in the future are proposed to provide reference for the trusted intelligence fusion and provide support for intelligent situation analysis and auxiliary decision making.

The process of advancement of artificial intelligence (hereinafter: AI) seen in recent years results in breakthroughs in many areas of human life, such as medicine, agriculture, and science. However, despite its many advantages and benefits, it also inevitably creates room for abuse. This is particularly true of child pornography, where AI systems are increasingly being used to generate nude images of minors — both existing in reality and fictional. These cases, given much attention in the public debate, cause doubts as to whether existing normative solutions are suitable to combat this new phenomenon. The article aims to answer the question of whether the existing law makes it possible to successfully prosecute perpetrators who use AI systems to generate child pornography (including that depicting fictional charac ters). In addition, it also offers an analysis of the criminal liability of the developers of the AI systems used in this process and of the hosting providers managing the websites used to distribute such pornographic content.

The rapid expansion of voice-based technologies across diverse applications underscores the critical need for robust security measures against audio spoofing attacks. This paper comprehensively examines publicly available datasets that have been developed to detect audio spoof attacks. The research encompasses a compilation of datasets, including ASVspoof dataset series (2019, 2021), Voice Spoofing Detection Corpus (VSDC), Voice Impersonation Corpus in Hindi Language (VIHL) and DEepfake CROss-lingual evaluation dataset (DECRO), covering various spoofing attack scenarios of English, Hindi and Chinese languages. In the first part of the paper, a baseline for the proposed research work has been developed by comparing the performances of state-of-the-art baseline Linear frequency cepstral coefficient (LFCC) features with application of four different machine learning classifiers Random forest (RF), K-nearest neighbor (KNN), eXtreme gradient boosting (XGBoost), and Naïve Bayes (NB) at the backend, over these four different datasets. In second part of the proposal, we have used novel feature combination of Mel Spectrogram-Residual Network41 (ResNet41)-Linear discriminant analysis (LDA) and Gammatone Spectrogram-ResNet41-LDA, one by one, with application of same set of machine learning classifiers at the backend. The combination of Gammatone spectrogram-ResNet41-LDA along with XGBoost classifier has achieved an Equal Error Rate (EER) of 1.7, 1.28, 0.5, 0.36, 0.03, 0.07, and 0.9% for ASVspoof 2019 Logical Access (LA), ASVspoof 2019 Physical Access (PA), ASVspoof 2021 Deepfake, VSDC, DECRO English, DECRO Chinese, and VIHL datasets, respectively. Hence, the proposed research work in this paper achieves the objective of assessing the feasibility and utility of publicly available state of the art datasets for training and testing advanced algorithms in identifying manipulated audio. [ABSTRACT FROM AUTHOR]

. As a result of large-scale digitalization of all spheres of human activity and the rapid introduction of artificial intelligence technologies, the need has arisen for forensic support for legal proceedings in cases in which artificial intelligence has a role. The most pressing tasks solved by forensic computer expert units are the study of the facts of unlawful (mainly criminal) use of artificial intelligence, the use of artificial intelligence to create new and improve existing methods of computer forensics, forensic analysis of products using artificial intelligence technologies in order to establish compliance of the final product with the technical specifications for its creation, as well as a comprehensive forensic the analysis is carried out either within a forensic computer examination, or comprehensively, with the involvement of specialists in the field of forensic linguistics, forensic phonoscopic and other types of examinations. Identifying distortions in metadata is an illustrative example of improving forensic methods for analyzing digital images using artificial intelligence technology.

Abstract In this paper, we undertake a novel two-pronged investigation into the human recognition of deepfake speech, addressing critical gaps in existing research. First, we pioneer an evaluation of the impact of prior information on deepfake recognition, setting our work apart by simulating real-world attack scenarios where individuals are not informed in advance of deepfake exposure. This approach simulates the unpredictability of real-world deepfake attacks, providing unprecedented insights into human vulnerability under realistic conditions. Second, we introduce a novel metric to evaluate the quality of deepfake audio. This metric facilitates a deeper exploration into how the quality of deepfake speech influences human detection accuracy. By examining both the effect of prior knowledge about deepfakes and the role of deepfake speech quality, our research reveals the importance of these factors, contributes to understanding human vulnerability to deepfakes, and suggests measures to enhance human detection skills.

Abstract In the last few years, research on the detection of AI-generated videos has focused exclusively on detecting facial manipulations known as deepfakes. Much less attention has been paid to the detection of artificial non-facial fake videos. In this paper, we address a new forensic task, namely, the detection of fake videos of human body reenactment. To this purpose, we consider videos generated by the “Everybody Dance Now” framework. To accomplish our task, we have constructed and released a novel dataset of fake videos of this kind, referred to as FakeDance dataset. Additionally, we propose two forgery detectors to study the detectability of FakeDance kind of videos. The first one exploits spatial–temporal clues of a given video by means of hand-crafted descriptors, whereas the second detector is an end-to-end detector based on Convolutional Neural Networks (CNNs) trained on purpose. Both detectors have their peculiarities and strengths, working well in different operative scenarios. We believe that our proposed dataset together with the two detectors will contribute to the research on the detection of non-facial fake videos generated by means of AI.

Introduction/purpose: Artificial intelligence can be used for both positive and negative purposes. In recent years, the use of deepfake technology has attracted significant attention. Deepfake technology replaces a person's face and creates events that never happened. While the use of deepfake was more noticeable in the past, the technology has advanced so rapidly that today it is impossible to determine if the content is fake or not. As a result, there is erosion of trust in the media and political institutions, manipulation of public discourse, as well as the spread of disinformation and fake news. The aim of this work is to examine the methods of creating deepfake content and explore the possibilities for detecting such content. A special focus is placed on investigating the dark side of deepfake technology, i.e., the negative purposes for which deepfake technology can be used. Methods: Through the use of literature review methods and content analysis, this work has provided a systematization of knowledge about deepfake technology, as well as an analysis of relevant data in this field regarding the potential misuse of deepfake technology. Deepfake technology and its use are viewed from a security perspective, i.e., how the use of these technologies can pose a social hazard. Future research should be designed to be multidisciplinary, integrating knowledge from social sciences (security, sociology, psychology) and technical sciences (information technology). Results: The results of this research show that in a positive context, the use of deepfake is associated with medicine, the film industry, entertainment, and creative endeavors. However, deepfake is often used to create pornographic content, revenge porn, fake news, and various types of fraud. Conclusion: Deepfake technology is neutral in the sense that the purpose of its use depends on the individual creating the content. The use of both artificial intelligence and deepfake technology raises complex legal and ethical questions. Although there is noticeable potential for societal improvement offered by these technologies, deepfake technology simultaneously poses a serious risk to human rights, democracy, and national security. Therefore, the misuse of deepfake technologies represents a social hazard for the entire population of any country. Women are particularly vulnerable due to the possibility of creating pornographic content and revenge porn using deepfake technology, although victims of this act can also be men.

Abstract While deep learning technologies have made remarkable progress in generating deepfakes, their misuse has become a well-known concern. As a result, the ubiquitous usage of deepfakes for increasing false information poses significant risks to the security and privacy of individuals. The primary objective of audio spoofing detection is to identify audio generated through numerous AI-based techniques. Several techniques for fake audio detection already exist using machine learning algorithms. However, they lack generalization and may not identify all types of AI-synthesized audios such as replay attacks, voice conversion, and text-to-speech (TTS). In this paper, a deep layered model, i.e., VGGish, along with an attention block, namely Convolutional Block Attention Module (CBAM) for spoofing detection, is introduced. Our suggested model successfully classifies input audio into two classes: Fake and Real, converting them into mel-spectrograms, and extracting their most representative features due to the attention block. Our model is a significant technique to utilize for audio spoofing detection due to a simple layered architecture. It captures complex relationships in audio signals due to both spatial and channel features present in an attention module. To evaluate the effectiveness of our model, we have conducted in-depth testing using the ASVspoof 2019 dataset. The proposed technique achieved an EER of 0.52% for Physical Access (PA) attacks and 0.07 % for Logical Access (LA) attacks.

Generative AI (GenAI) can generate high-resolution and complex content mimicking the creativity of humans, thereby benefiting industries such as gaming, entertainment, and product design. In recent times, AI-generated fake videos, commonly referred to as deepfakes, have become more commonplace and convincing. An additional deepfake technique, face warping, uses digital processing to noticeably distort shapes on a face. Tracking such warping in images and videos is crucial and preventing its use for destructive purposes. A technique is proposed for detecting and localizing face warped areas in video. The input video is extracted to perform various image pre-processing techniques that refine the video into a format that is more likely to classify the classes efficiently. Transfer learning is employed, and the pre-trained model is adopted to train using Convolutional Neural Network (CNN) with the source videos to identify face warping. Based on the experimental results, it was determined that the proposed model detects and localizes the warped areas of the face satisfactorily with an accuracy of 89.25%.

In this paper, we undertake a novel two-pronged investigation into the human recognition of deepfake speech, addressing critical gaps in existing research. First, we pioneer an evaluation of the impact of prior information on deepfake recognition, setting our work apart by simulating real-world attack scenarios where individuals are not informed in advance of deepfake exposure. This approach simulates the unpredictability of real-world deepfake attacks, providing unprecedented insights into human vulnerability under realistic conditions. Second, we introduce a novel metric to evaluate the quality of deepfake audio. This metric facilitates a deeper exploration into how the quality of deepfake speech influences human detection accuracy. By examining both the effect of prior knowledge about deepfakes and the role of deepfake speech quality, our research reveals the importance of these factors, contributes to understanding human vulnerability to deepfakes, and suggests measures to enhance human detection skills. [ABSTRACT FROM AUTHOR]

In the last few years, research on the detection of AI-generated videos has focused exclusively on detecting facial manipulations known as deepfakes. Much less attention has been paid to the detection of artificial non-facial fake videos. In this paper, we address a new forensic task, namely, the detection of fake videos of human body reenactment. To this purpose, we consider videos generated by the "Everybody Dance Now" framework. To accomplish our task, we have constructed and released a novel dataset of fake videos of this kind, referred to as FakeDance dataset. Additionally, we propose two forgery detectors to study the detectability of FakeDance kind of videos. The first one exploits spatial–temporal clues of a given video by means of hand-crafted descriptors, whereas the second detector is an end-to-end detector based on Convolutional Neural Networks (CNNs) trained on purpose. Both detectors have their peculiarities and strengths, working well in different operative scenarios. We believe that our proposed dataset together with the two detectors will contribute to the research on the detection of non-facial fake videos generated by means of AI. [ABSTRACT FROM AUTHOR]

Deepfakes have become widespread and have continued to develop rapidly in recent years. In addition to the use of deepfakes in movies and for humorous purposes, this technology has also begun to pose a threat to many companies and politicians. Deepfake detection is critical to the prevention of this threat. In this study, a Choquet fuzzy integral-based deepfake detection method is proposed to increase overall performance by combining the results obtained from different deepfake detection methods. Three different deepfake detection models were used in the study: XceptionNet, which has better performance in detecting real images/videos; EfficientNet, which has better performance in detecting fake videos; and a model based on their hybrid uses. The proposed method based on the Choquet fuzzy integral aims to eliminate the shortcomings of these methods by using each of the other methods. As a result, a higher performance was achieved with the proposed method than found when all three methods were used individually. As a result of the testing and validation studies carried out on FaceForensics++, DFDC, Celeb-DF, and DeepFake-TIMIT datasets, the individual performance levels of the algorithms used were 81.34%, 82.78%, and 79.15% on average, according to the AUC curve, while the level of 97.79% was reached with the proposed method. Considering that the average performance of the three methods across all datasets is 81.09%, it can be seen that an improvement of approximately 16.7% is achieved. In the FaceForensics++ dataset, in which individual algorithms are more successful, the performance of the proposed method reaches the highest AUC value, 99.8%. It can be seen that the performance rates can be increased by changing the individual methods discussed in the proposed method. We believe that the proposed method will inspire researchers and will be further developed. [ABSTRACT FROM AUTHOR]

AbstractWe investigated whether people show signs of conflict detection in both more implicit and explicit judgments about the authenticity of short video clips depicting interviews with famous American actors. If so, they would be less confident when incorrectly seeing deepfakes as authentic than when correctly seeing authentic videos as authentic. Participants (N = 128; Mage = 33.7, SD = 12.1) from the USA were recruited on Prolific. Results showed that participants were more accurate at recognising deepfakes and less accurate at recognising authentic videos when they were explicitly asked to judge if a video was authentic or deepfake compared to more implicit authenticity judgments. Interestingly, they showed signs of conflict detection both when making more implicit and explicit authenticity judgments. These findings are relevant for the literature on both conflict detection in reasoning and decision-making and on deepfake recognition, as well as for research on training people to learn to recognise deepfakes. [ABSTRACT FROM AUTHOR]

Fandom as an interpretive community is the frontier for rich insights into the multi-layered interactions and practices between individual users, communities and intelligent machines. To understand the challenges and opportunities Artificial Intelligence (AI) presents to contemporary media and culture, we discuss how fans engage with AI, as fandom provides meaningful insights into interactions between individual technology users, the collective and machines. We propose rethinking participatory culture as human–community–machine interactions to understand the wider implications of AI to society and culture. We outline three emerging phenomena and potential consequences of fans' engagement with AI: (1) fan labour made (un)easy, (2) parasocial interactions (un)familiarised and (3) realities (un)settled. Our conceptualisation transcends existing computer science research, which assumes technology users as isolated individuals and also fan studies, which largely focus on text-audience relationships and tend to take digital technologies for granted as the preconditions of fans' creative and playful practices. [ABSTRACT FROM AUTHOR]

Advances in deep learning technology have enabled the generation of more realistic deepfakes, which not only endanger individuals' identities but also exploit vulnerabilities in face recognition systems. The majority of existing deepfake detection methods have primarily focused on RGB-based analysis, offering unreliable performance in terms of detection accuracy and time. To address the issue, a grayscale-based deepfake detection method has recently been proposed. This method significantly reduces detection time while providing comparable accuracy to RGB-based methods. However, despite its significant effectiveness, the "key components" that directly affect the performance of grayscale-based deepfake detection have not been systematically analyzed. In this paper, we target three key components: RGB-to-grayscale conversion method, brightness level in grayscale, and resolution level in grayscale. To analyze their impacts on the performance of grayscale-based deepfake detection, we conducted comprehensive evaluations, including component-wise analysis and comparative analysis using real-world datasets. For each key component, we quantitatively analyzed its characteristics' performance and identified differences between them. Moreover, we successfully verified the effectiveness of an optimal combination of the key components by comparing it with existing deepfake detection methods. [ABSTRACT FROM AUTHOR]

Copyright of Revista Foco (Interdisciplinary Studies Journal) is the property of Revista Foco and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Deep generative models, especially Generative Adversarial Networks (GANs), have recently demonstrated outstanding performance in real-world applications such as image generation and content production for large-scale public datasets and social media platforms, enabling high-resolution compelling fake content generation. Deepfakes have raised global concerns and disbelief due to the potential implications of misleading multimedia. Several algorithms to detect deepfakes have emerged; however, most rely on deep learning and video datasets. So, an automated approach is needed to detect the generated deepfakes. This paper presents a deepfake detection technique employing simple machine learning to identify low-resolution deepfakes and introduces a dataset that contains high-resolution, low-resolution, and mixed images. The method utilizes classification algorithms and an ensemble model in the frequency domain. K-fold cross-validation determines an average detection accuracy of 99.97% for high-resolution datasets using random forest, 98.27% for low-resolution datasets using SVM polynomial, and 98.72% for mixed datasets using voting classifier. [ABSTRACT FROM AUTHOR]

Introduction/purpose: Artificial intelligence can be used for both positive and negative purposes. In recent years, the use of deepfake technology has attracted significant attention. Deepfake technology replaces a person's face and creates events that never happened. While the use of deepfake was more noticeable in the past, the technology has advanced so rapidly that today it is impossible to determine if the content is fake or not. As a result, there is erosion of trust in the media and political institutions, manipulation of public discourse, as well as the spread of disinformation and fake news. The aim of this work is to examine the methods of creating deepfake content and explore the possibilities for detecting such content. A special focus is placed on investigating the dark side of deepfake technology, i.e., the negative purposes for which deepfake technology can be used. Methods: Through the use of literature review methods and content analysis, this work has provided a systematization of knowledge about deepfake technology, as well as an analysis of relevant data in this field regarding the potential misuse of deepfake technology. Deepfake technology and its use are viewed from a security perspective, i.e., how the use of these technologies can pose a social hazard. Future research should be designed to be multidisciplinary, integrating knowledge from social sciences (security, sociology, psychology) and technical sciences (information technology). Results: The results of this research show that in a positive context, the use of deepfake is associated with medicine, the film industry, entertainment, and creative endeavors. However, deepfake is often used to create pornographic content, revenge porn, fake news, and various types of fraud. Conclusion: Deepfake technology is neutral in the sense that the purpose of its use depends on the individual creating the content. The use of both artificial intelligence and deepfake technology raises complex legal and ethical questions. Although there is noticeable potential for societal improvement offered by these technologies, deepfake technology simultaneously poses a serious risk to human rights, democracy, and national security. Therefore, the misuse of deepfake technologies represents a social hazard for the entire population of any country. Women are particularly vulnerable due to the possibility of creating pornographic content and revenge porn using deepfake technology, although victims of this act can also be men. [ABSTRACT FROM AUTHOR]

With the rapid progress of deepfake technology, the improper use of manipulated images and videos presenting synthetic faces has arisen as a noteworthy concern, thereby posing threats to both daily life and national security. While numerous CNN based deepfake face detection methods were proposed, most of the existing approaches encounter challenges in effectively capturing the image contents across different scales and positions. In this paper, we present a novel two-branch structural network, referred to as the Self-Attention Deepfake Face Discrimination Network (SADFFD). Specifically, a branch incorporating cascaded multi self-attention mechanism (SAM) modules, is parallelly integrated with EfficientNet-B4 (EffB4). The multi SAM branch supplies additional features that concentrate on image regions essential for discriminating between real and fake. The EffB4 network is adopted because of its efficiency by adjusting the resolution, depth, and width of the network. According to our comprehensive experiments conducted on FaceForensics++, Celeb-DF, and our self-constructed SAMGAN3 datasets, the proposed SADFFD demonstrated the highest detection accuracy, averaging 99.01% in FaceForensics++, 98.65% in Celeb-DF, and an impressive 99.99% in SAMGAN3, surpassing other state-of-the-art (SOTA) methods. • A novel two-branch CNN structure is proposed for deepfake face discrimination. • The self-attention mechanism is utilized to enhance the accuracy of discrimination. • FaceForensics++, Celeb-DF and our self-built dataset are used in evaluation in terms of detection accuracy. • Forged face images/videos from various generating methods are included in our evaluation datasets. • Comprehensive experiments demonstrate the superior performance of our proposed method in discriminating deepfake face. [ABSTRACT FROM AUTHOR]

Copyright of Romanian Journal of Intellectual Property Law / Revista Română de Dreptul Proprietăţii Intelectuale is the property of Universul Juridic Publishing House and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Japan Society for Fuzzy Theory & Intelligent Informatics is the property of Japan Society for Fuzzy Theory & Intelligent Informatics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Research on DeepFake detection using deep neural networks (DNNs) has gained more attention in an effort to detect and categorize DeepFakes. In essence, DeepFakes are regenerated content made by changing particular DNN model elements. In this study, a summary of DeepFake detection methods for images and videos involving faces will be given based on their effectiveness, outcomes, methodology, and type of detection method. We will analyze and categorize the many DeepFake-generating techniques now in use into five primary classes. DeepFake datasets are frequently used to train and test DeepFake models. We will also cover the latest developments in DeepFake dataset trends that are currently accessible. We will also examine the problems in building a generalized DeepFake detection model. Lastly, the difficulties in creating and identifying DeepFakes will be covered. [ABSTRACT FROM AUTHOR]

Today, the significance of biometrics is more pronounced than ever in accurately allowing access to valuable resources, from personal devices to highly sensitive buildings, as well as classified information. Researchers are pushing forward toward devising robust biometric systems with higher accuracy, fewer false positives and false negatives, and better performance. On the other hand, machine learning (ML) has been shown to play a key role in improving such systems. By constantly learning and adapting to users' changing biometric patterns, ML algorithms can improve accuracy and performance over time. The integration of ML algorithms with biometrics, however, introduces vulnerabilities in such systems. This article investigates the new issues of concern that come about because of the adoption of ML methods in biometric systems. Specifically, techniques to breach biometric systems, namely, data poisoning, model inversion, bias injection, and deepfakes, are discussed. Here, the methodology consisted of conducting a detailed review of the literature in which ML techniques have been adopted in biometrics. In this study, we included all works that have successfully applied ML and reported favorable results after this adoption. These articles not only reported improved numerical results but also provided sound technical justification for this improvement. There were many isolated, unsupported, and unjustified works about the major advantages of ML techniques in improving security, which were excluded from this review. Though briefly mentioned, we did not touch upon encryption/decryption aspects, and, accordingly, cybersecurity was excluded from this study. At the end, recommendations are made to build stronger and more secure systems that benefit from ML adoption while closing the door to adversarial attacks. [ABSTRACT FROM AUTHOR]

In this special issue 'Fact or Fake: Information, Misinformation, and Disinformation via Social Media', the Journal of Strategic Marketing presents a collection of papers that delve into various topics aimed at gaining a comprehensive understanding of the impacts of fake news on social media. The objective of this special issue is to enhance our comprehension of marketing theory and practice concerning solutions, prevention, and the effects of fake news propagated through social media platforms. The topics covered within the special issue include, but are not limited to (1) Organizational and regulatory strategies to counter the dissemination of false news on social media; (2) The influence of fake news on social media on consumer behavior; (3) The correlation between social media fake news, consumer perceptions of credibility and trustworthiness, and their self-efficacy in relation to purchasing intentions; (4) The phenomenon of an 'infodemic' characterized by disinformation and misinformation in the digital age; and (5) Perceptions of credibility surrounding disinformation and intentions to share such content across social media platforms. [ABSTRACT FROM AUTHOR]

Face manipulation is the process of modifying facial features in videos or images to produce a variety of artistic or deceptive effects. Face manipulation detection looks for altered or falsified visual media in order to differentiate between real and fake facial photographs or videos. The intricacy of the techniques used makes it difficult to detect face manipulation, particularly in the context of technologies like DeepFake. This paper presents an efficient framework based on Hybrid Learning and Kernel Principal Component Analysis (KPCA) to extract more extensive and refined face-manipulating attributes. The proposed method utilizes the EfficientNetV2-L model for feature extraction, topped up with KPCA for feature dimensionality reduction, to distinguish between real and fake facial images. The proposed method is robust to various facial manipulations techniques such as identity swap, expression swap, attribute-based manipulation, and entirely synthesized faces. In this work, data augmentation is used to solve the problem of class imbalance present in the dataset. The proposed method has less execution time while achieving an accuracy of 99.3% and an F1 Score of 0.98 on the Diverse Fake Face Dataset (DFFD). [ABSTRACT FROM AUTHOR]

Copyright of Filosofija, Sociologija is the property of Lithuanian Academy of Sciences Publishers and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

While deep learning technologies have made remarkable progress in generating deepfakes, their misuse has become a well-known concern. As a result, the ubiquitous usage of deepfakes for increasing false information poses significant risks to the security and privacy of individuals. The primary objective of audio spoofing detection is to identify audio generated through numerous AI-based techniques. Several techniques for fake audio detection already exist using machine learning algorithms. However, they lack generalization and may not identify all types of AI-synthesized audios such as replay attacks, voice conversion, and text-to-speech (TTS). In this paper, a deep layered model, i.e., VGGish, along with an attention block, namely Convolutional Block Attention Module (CBAM) for spoofing detection, is introduced. Our suggested model successfully classifies input audio into two classes: Fake and Real, converting them into mel-spectrograms, and extracting their most representative features due to the attention block. Our model is a significant technique to utilize for audio spoofing detection due to a simple layered architecture. It captures complex relationships in audio signals due to both spatial and channel features present in an attention module. To evaluate the effectiveness of our model, we have conducted in-depth testing using the ASVspoof 2019 dataset. The proposed technique achieved an EER of 0.52% for Physical Access (PA) attacks and 0.07 % for Logical Access (LA) attacks. [ABSTRACT FROM AUTHOR]

Generative adversarial network (GAN)-generated image detection is a crucial yet challenging problem. The advancement of diverse generative models makes it simpler to build realistic synthetic images, but it also increases the likelihood of using images maliciously. Recent techniques of fake image detection often overfit to specific GANs, incapable of generalizing to other GANs. Each GAN leaves its distinct fingerprint on the images it generates. We propose a simple and compact attention network that exploits high-frequency and noise residual patterns of images. We design two-channel image representations in the preprocessing phase, with one channel using a bilateral high pass filter (BiHPF) for high-frequency patterns and the other using photo response non-uniformity (PRNU) for noise residuals capturing from GAN-generated and real images. The feature maps pass through the attention network with a dense layer for classification tasks. We assess the generalizability and robustness of the model through extensive experiments. The model is evaluated on a benchmark dataset in various settings, including cross-category, cross-GAN models with varying class settings and different color manipulations. This study demonstrates that the proposed model outperforms state-of-the-art (SOTA) methods by approximately 5% in different experiment settings. • Each GAN leaves a distinctive noise imprint on the images it generates. • A simple and small two-channel CNN framework based on an attention mechanism. • The RGB image is transformed into a 2-channel image by using BiHPF and PRNU. • These features are then used as input to the CNN classifier. • A generalized and robust model evaluated in cross-category and cross-GAN. [ABSTRACT FROM AUTHOR]