Search

In contexts requiring user authentication, such as financial, legal, and administrative systems, signature verification emerges as a pivotal biometric method. Specifically, handwritten signature verification stands out prominently for document authentication. Despite the effectiveness of triplet loss similarity networks in extracting and comparing signatures with forged samples, conventional deep learning models often inadequately capture individual writing styles, resulting in suboptimal performance. Addressing this limitation, our study employs a triplet loss Siamese similarity network for offline signature verification, irrespective of the author. Through experimentation on five publicly available signature datasets—4NSigComp2012, SigComp2011, 4NSigComp2010, and BHsig260—various distance measure techniques alongside the triplet Siamese Similarity Network (tSSN) were evaluated. Our findings underscore the superiority of the tSSN approach, particularly when coupled with the Manhattan distance measure, in achieving enhanced verification accuracy, thereby demonstrating its efficacy in scenarios characterized by close signature similarity. [ABSTRACT FROM AUTHOR]

In recent years, significant advancements in the field of machine learning have influenced the domain of image restoration. While these technological advancements present prospects for improving the quality of images, they also present difficulties, particularly the proliferation of manipulated or counterfeit multimedia information on the internet. The objective of this paper is to provide a comprehensive review of existing inpainting algorithms and forgery detections, with a specific emphasis on techniques that are designed for the purpose of removing objects from digital images. In this study, we will examine various techniques encompassing conventional texture synthesis methods as well as those based on neural networks. Furthermore, we will present the artifacts frequently introduced by the inpainting procedure and assess the state-of-the-art technology for detecting such modifications. Lastly, we shall look at the available datasets and how the methods compare with each other. Having covered all the above, the outcome of this study is to provide a comprehensive perspective on the abilities and constraints of detecting object removal via the inpainting procedure in images. [ABSTRACT FROM AUTHOR]

With the development of sensor and communication technologies, the Internet of Things (IoT) subsystem is gradually becoming a crucial part in vehicles. It can effectively enhance functionalities of vehicles. However, new attack types are also emerging. For example, a driver with the smart key in their pocket can push the start button to start a car. At the same time, security issues in the push-to-start scenario are pervasive, such as smart key forgery. In this study, we propose a vehicle Passive Entry Passive Start (PEPS) system that adopts deep learning algorithms to recognize the driver using the electrocardiogram (ECG) signals measured on the driver's smart watch. ECG signals are used for personal identification. Smart watches, serving as new smart keys of the PEPS system, can improve convenience and security. In the experiment, we consider commercial smart watches capable of sensing ECG signals. The sample rate and precision are typically lower than those of a 12-lead ECG used in hospitals. The experimental results show that Long Short-Term Memory (LSTM) models achieve the best accuracy score for identity recognition (91%) when a single ECG cycle is used. However, it takes at least 30 min for training. The training of a personalized Auto Encoder model takes only 5 min for each subject. When 15 continuous ECG cycles are sensed and used, this can achieve 100% identity accuracy. As the personalized Auto Encoder model is an unsupervised learning one-class recognizer, it can be trained using only the driver's ECG signal. This will simplify the management of ECG recordings extremely, as well as the integration of the proposed technology into PEPS vehicles. A FIDO (Fast Identify Online)-like environment for the proposed PEPS system is discussed. Public key cryptography is adopted for communication between the smart watch and the PEPS car. The driver is first verified on the smart watch via local ECG biometric authentication, and then identified by the PEPS car. Phishing attacks, MITM (man in the middle) attacks, and replay attacks can be effectively prevented. [ABSTRACT FROM AUTHOR]

While there are many verification studies on signature images using deep learning algorithms in the literature, there is a lack of studies on the classification of signature images. Signatures are used as a means of identification for banking, security controls, symmetry, certificates, and contracts. In this study, the aim was to design network architectures that work very fast in areas that require only signature images. For this purpose, a new Si-CNN network architecture with existing layers was designed. Afterwards, a new loss function and layer (Si-CL), a novel architecture using Si-CL as classification layer in Si-CNN to increase the performance of this architecture, was designed. This architecture was called Si-CNN+NC (New Classification). Si-CNN and Si-CNN+NC were trained with two datasets. The first dataset which was used for training is the "C-Signatures" (Classification Signatures) dataset, which was created to test these networks. The second dataset is the "Cedar" dataset, which is a benchmark dataset. The number of classes and sample numbers in the two datasets are symmetrical with each other. To compare the performance of the trained networks, four of the most well-known pre-trained networks, GoogleNet, DenseNet201, Inceptionv3, and ResNet50, were also trained with the two datasets with transfer learning. The findings of the study showed that the proposed network models can learn features from two different handwritten signature images and achieve higher accuracy than other benchmark models. The test success of the trained networks showed that the Si-CNN+NC network outperforms the others, in terms of both accuracy and speed. Finally, Si-CNN and Si-CNN+NC networks were trained with the gold standard dataset MNIST and showed superior performance. Due to its superior performance, Si-CNN and Si-CNN+NC can be used by signature experts as an aid in a variety of applications, including criminal detection and forgery. [ABSTRACT FROM AUTHOR]

This paper addresses the enhancement of modern security through the integration of electrocardiograms (ECGs) into biometric authentication systems. As technology advances, the demand for reliable identity authentication systems has grown, given the rise in breaches associated with traditional techniques that rely on unique biological and behavioral traits. These techniques are emerging as more reliable alternatives. Among the biological features used for authentication, ECGs offer unique advantages, including resistance to forgery, real-time detection, and continuous identification ability. A key contribution of this work is the introduction of a variant of the ECG time-slicing technique that outperforms existing ECG-based authentication methods. By leveraging machine learning algorithms and tailor-made compact data learning techniques, this research presents a more robust, reliable biometric authentication system. The findings could lead to significant advancements in network information security, with potential applications across various internet and mobile services. [ABSTRACT FROM AUTHOR]

Recent advances in Generative Artificial Intelligence (AI) have increased the possibility of generating hyper-realistic DeepFake videos or images to cause serious harm to vulnerable children, individuals, and society at large with misinformation. To overcome this serious problem, many researchers have attempted to detect DeepFakes using advanced machine learning techniques and advanced fusion techniques. This paper presents a detailed review of past and present DeepFake detection methods with a particular focus on media-modality fusion and machine learning. This paper also provides detailed information on available benchmark datasets in DeepFake detection research. This review paper addressed the 67 primary papers that were published between 2015 and 2023 in DeepFake detection, including 55 research papers in image and video DeepFake detection methodologies and 15 research papers on identifying and verifying speaker authentication. This paper offers lucrative information on DeepFake detection research and offers a unique review analysis of advanced machine learning and modality fusion that sets it apart from other review papers. This paper further offers informed guidelines for future work in DeepFake detection utilizing advanced state-of-the-art machine learning and information fusion models that should support further advancement in DeepFake detection for a sustainable and safer digital future. [ABSTRACT FROM AUTHOR]

With the expansion of wireless mobile networks into both the daily lives of individuals as well as into the widely developing market of connected devices, communication is an increasingly attractive target for attackers. As the complexity of mobile cellular systems grows and the respective countermeasures are implemented to secure data transmissions, the attacks have become increasingly sophisticated on the one hand, but at the same time the system complexity can open up expanded opportunities for security and privacy breaches. After an in-depth summary of possible entry points to attacks to mobile networks, this paper first briefly reviews the basic principles of the physical layer implementation of 4G/5G systems, then gives an overview of possible attacks from a physical layer perspective. It also provides an overview of the software frameworks and hardware tool-software defined radios currently in use for experimenting with 4G/5G mobile networks, and it discusses their basic capabilities. In the final part, the paper summarizes the currently most promising families of techniques to detect illegitimate base stations—the machine-learning-based, localization-based, and behavior-based methods. [ABSTRACT FROM AUTHOR]

Leukemia is a malignant disease that impacts explicitly the blood cells, leading to life-threatening infections and premature mortality. State-of-the-art machine-enabled technologies and sophisticated deep learning algorithms can assist clinicians in early-stage disease diagnosis. This study introduces an advanced end-to-end approach for the automated diagnosis of acute leukemia classes acute lymphocytic leukemia (ALL) and acute myeloid leukemia (AML). This study gathered a complete database of 44 patients, comprising 670 ALL and AML images. The proposed deep model's architecture consisted of a fusion of graph theory and convolutional neural network (CNN), with six graph Conv layers and a Softmax layer. The proposed deep model achieved a classification accuracy of 99% and a kappa coefficient of 0.85 for ALL and AML classes. The suggested model was assessed in noisy conditions and demonstrated strong resilience. Specifically, the model's accuracy remained above 90%, even at a signal-to-noise ratio (SNR) of 0 dB. The proposed approach was evaluated against contemporary methodologies and research, demonstrating encouraging outcomes. According to this, the suggested deep model can serve as a tool for clinicians to identify specific forms of acute leukemia. [ABSTRACT FROM AUTHOR]

The swift explosion of Internet of Things (IoT) devices has brought about a new era of interconnectivity and ease of use while simultaneously presenting significant security concerns. Intrusion Detection Systems (IDS) play a critical role in the protection of IoT ecosystems against a wide range of cyber threats. Despite research advancements, challenges persist in improving IDS detection accuracy, reducing false positives (FPs), and identifying new types of attacks. This paper presents a comprehensive analysis of recent developments in IoT, shedding light on detection methodologies, threat types, performance metrics, datasets, challenges, and future directions. We systematically analyze the existing literature from 2016 to 2023, focusing on both machine learning (ML) and non-ML IDS strategies involving signature, anomaly, specification, and hybrid models to counteract IoT-specific threats. The findings include the deployment models from edge to cloud computing and evaluating IDS performance based on measures such as accuracy, FP rates, and computational costs, utilizing various IoT benchmark datasets. The study also explores methods to enhance IDS accuracy and efficiency, including feature engineering, optimization, and cutting-edge solutions such as cryptographic and blockchain technologies. Equally, it identifies key challenges such as the resource-constrained nature of IoT devices, scalability, and privacy issues and proposes future research directions to enhance IoT-based IDS and overall ecosystem security. [ABSTRACT FROM AUTHOR]

This document is a summary of a special issue of the journal Electronics titled "AI-Driven Network Security and Privacy." The issue focuses on various topics related to network security and privacy, including malware detection, intrusion detection, malware classification, domain name detection, encryption schemes, model robustness evaluation, traffic obfuscation, APT attack event extraction, object detection, abnormal traffic detection, data management, sentiment analysis, deepfake dataset evaluation, evasion attacks, face recognition, remote sensing image object detection, and target tracking in UAV videos. Each contribution presents a specific method or approach to address the challenges in their respective areas. The summary provides a brief overview of each contribution's main findings and methodologies. The document also discusses the future directions of AI-driven network security and privacy, including secure data sharing, privacy protection, threat detection and prevention, and automated response and repair. The authors express their gratitude to the researchers, reviewers, and editorial staff involved in the publication of the articles. [Extracted from the article]

Milk is a kind of dairy product with high nutritive value. Tracing the origin of milk can uphold the interests of consumers as well as the stability of the dairy market. In this study, a fuzzy direct linear discriminant analysis (FDLDA) is proposed to extract the near-infrared spectral information of milk by combining fuzzy set theory with direct linear discriminant analysis (DLDA). First, spectral data of the milk samples were collected by a portable NIR spectrometer. Then, the data were preprocessed by Savitzky–Golay (SG) and standard normal variables (SNV) to reduce noise, and the dimensionality of the spectral data was decreased by principal component analysis (PCA). Furthermore, linear discriminant analysis (LDA), DLDA, and FDLDA were employed to transform the spectral data into feature space. Finally, the k-nearest neighbor (KNN) classifier, extreme learning machine (ELM) and naïve Bayes classifier were used for classification. The results of the study showed that the classification accuracy of FDLDA was higher than DLDA when the KNN classifier was used. The highest recognition accuracy of FDLDA, DLDA, and LDA could reach 97.33%, 94.67%, and 94.67%. The classification accuracy of FDLDA was also higher than DLDA when using ELM and naïve Bayes classifiers, but the highest recognition accuracy was 88.24% and 92.00%, respectively. Therefore, the KNN classifier outperformed the ELM and naïve Bayes classifiers. This study demonstrated that combining FDLDA, DLDA, and LDA with NIR spectroscopy as an effective method for determining the origin of milk. [ABSTRACT FROM AUTHOR]

Increasing global credit card usage has elevated it to a preferred payment method for daily transactions, underscoring its significance in global financial cybersecurity. This paper introduces a credit card fraud detection (CCFD) system that integrates federated learning (FL) with blockchain technology. The experiment employs FL to establish a global learning model on the cloud server, which transmits initial parameters to individual local learning models on fog nodes. With three banks (fog nodes) involved, each bank trains its learning model locally, ensuring data privacy, and subsequently sends back updated parameters to the global learning model. Through the integration of FL and blockchain, our system ensures privacy preservation and data protection. We utilize three machine learning and deep neural network learning algorithms, RF, CNN, and LSTM, alongside deep optimization techniques such as ADAM, SGD, and MSGD. The SMOTE oversampling technique is also employed to balance the dataset before model training. Our proposed framework has demonstrated efficiency and effectiveness in enhancing classification performance and prediction accuracy. [ABSTRACT FROM AUTHOR]

It is commonly known that the present systems and techniques used in education are outdated. In 1983, UNESCO had already called attention to this, calling present techniques archaic and inefficient. Though a lot of new developments have been achieved and a lot of commendable work has been carried out to remedy particular shortfalls in present systems, no literature was found that develops a concise and complete model for an education approach that maps the use of emergent technologies and techniques to improve on shortfalls in present teaching and learning paradigms. This paper reviews emergent technologies and techniques and their impacts and successes, to propose a combined model for online education to improve the effectiveness, accessibility and impact of teaching and learning activities. This paper concludes by presenting the possible future scope of education and employment structures by examining the possible impacts of the proposed model. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) reflects the internetworking of numerous devices with limited computational capabilities. Given the ad-hoc network formation and the dynamic nature of node membership, secure device authentication mechanisms are critical. This paper proposes a novel two-factor authentication protocol for IoT devices. The protocol integrates physical unclonable functions (PUFs) and radio frequency fingerprints (RFFs), providing a unique identification method for each device. Compared with existing PUF-based schemes, the proposed protocol facilitates the mutual authentication of two devices without the need for a trusted third party. Our design is resilient to the intrinsic noise associated with PUFs and RFFs, ensuring reliable authentication, even under various operational conditions. Furthermore, we have implemented an obfuscation technique to secure shared authentication data against eavesdropping attempts aimed at modeling the security primitive, i.e., the PUF, through machine learning algorithms. We have validated the performance of our protocol and demonstrated its efficacy against various security threats, including impersonation, message replay, and PUF modeling attacks. Notably, the validation results indicate that predicting any given PUF response bit's accuracy does not exceed 56%, making it as unpredictable as a random guess. [ABSTRACT FROM AUTHOR]

Software defect prediction is an important part of software development, which aims to use existing historical data to predict future software defects. Focusing on the model performance and communication efficiency of cross-project software defect prediction, this paper proposes an efficient communication-based federated meta-learning (ECFML) algorithm. The lightweight MobileViT network is used as the meta-learner of the Model Agnostic Meta-Learning (MAML) algorithm. By learning common knowledge on the local data of multiple clients, and then fine-tuning the model, the number of unnecessary iterations is reduced, and communication efficiency is improved while reducing the number of parameters. The gradient information model is encrypted using the differential privacy of the Laplace mechanism, and the optimal privacy budget is determined through experiments. Experiments on three public datasets (AEEEM, NASA, and Relink) verified the effectiveness of ECFML in terms of parameter quantity, convergence, and model performance of cross-project software defect prediction. [ABSTRACT FROM AUTHOR]

The echo state network (ESN) is a recurrent neural network that has yielded state-of-the-art results in many areas owing to its rapid learning ability and the fact that the weights of input neurons and hidden neurons are fixed throughout the learning process. However, the setting procedure for initializing the ESN's recurrent structure may lead to difficulties in designing a sound reservoir that matches a specific task. This paper proposes an improved pre-training method to adjust the model's parameters and topology to obtain an adaptive reservoir for a given application. Two strategies, namely global random selection and ensemble training, are introduced to pre-train the randomly initialized ESN model. Specifically, particle swarm optimization is applied to optimize chosen fixed and global weight values within the network, and the reliability and stability of the pre-trained model are enhanced by employing the ensemble training strategy. In addition, we test the feasibility of the model for time series prediction on six benchmarks and two real-life datasets. The experimental results show a clear enhancement in the ESN learning results. Furthermore, the proposed global random selection and ensemble training strategies are also applied to pre-train the extreme learning machine (ELM), which has a similar training process to the ESN model. Numerical experiments are subsequently carried out on the above-mentioned eight datasets. The experimental findings consistently show that the performance of the proposed pre-trained ELM model is also improved significantly. The suggested two strategies can thus enhance the ESN and ELM models' prediction accuracy and adaptability. [ABSTRACT FROM AUTHOR]

From the information forensics point of view, it is important to correctly classify between natural images (outputs of digital cameras) and computer-graphics images (outputs of advanced graphics rendering engines), so as to know the source of the images and the authenticity of the scenes described in the images. It is challenging to achieve good classification performance when the forensic classifier is tested on computer-graphics images generated by unknown rendering engines and when we have a limited number of training samples. In this paper, we propose two simple yet effective methods to improve the classification performance under such challenging situations, respectively based on data augmentation and the combination of local and global prediction results. Compared with existing methods, our methods are conceptually simple and computationally efficient, while achieving satisfying classification accuracy. Experimental results on datasets comprising computer-graphics images generated by four popular and advanced graphics rendering engines demonstrate the effectiveness of the proposed methods. [ABSTRACT FROM AUTHOR]

Heritage science is an established and thriving field of enquiry. Initially considered as inherently cross-disciplinary, encompassing both the needs of conservators and practitioners and the high-quality evidence produced by scientists, heritage science has, through its expansion in recent years, formed a discipline in its own right. Here, we examine how heritage science can, and to an extent has, moved beyond the straightforward scientific analysis of historical materials and artefacts through an exploration of heritage science's interactions with four key themes: (i) historical and archival research, (ii) conservation practice, (iii) policy at governmental, organisational and institutional levels, and (iv) a view to how new technologies, such as machine learning and artificial intelligence, can shape the future of heritage science. Much of the review narrative is framed via the analysis of UK-based case studies; however, they deal with issues that are international in nature (universal) and therefore transcend the UK context. Taken together, we demonstrate that heritage science as a discipline is capable of directly instigating or (re-)framing new areas or avenues of research, as well as enhancing and feeding into existing research questions, and has adapted and evolved along with emerging technologies and funding opportunities. [ABSTRACT FROM AUTHOR]

This study investigates the application of machine learning techniques for cyberattack prevention in Internet of Things (IoT) systems, focusing on the specific context of cyberattacks in Colombia. The research presents a comparative perspective on cyberattacks in Colombia, aiming to identify the most effective machine learning methods for mitigating and preventing such threats. The study evaluates the performance of logistic regression, naïve Bayes, perceptron, and k-nearest neighbors algorithms in the context of cyberattack prevention. Results reveal the strengths and weaknesses of these techniques in addressing the unique challenges posed by cyberattackers in Colombia's IoT infrastructure. The findings provide valuable insights for enhancing cybersecurity measures in the region and contribute to the broader field of IoT security. [ABSTRACT FROM AUTHOR]

Automatic data fusion is an important field of machine learning that has been increasingly studied. The objective is to improve the classification performance from several individual classifiers in terms of accuracy and stability of the results. This paper presents a comparative study on recent data fusion methods. The fusion step can be applied at early and/or late stages of the classification procedure. Early fusion consists of combining features from different sources or domains to form the observation vector before the training of the individual classifiers. On the contrary, late fusion consists of combining the results from the individual classifiers after the testing stage. Late fusion has two setups, combination of the posterior probabilities (scores), which is called soft fusion, and combination of the decisions, which is called hard fusion. A theoretical analysis of the conditions for applying the three kinds of fusion (early, late, and late hard) is introduced. Thus, we propose a comparative analysis with different schemes of fusion, including weaknesses and strengths of the state-of-the-art methods studied from the following perspectives: sensors, features, scores, and decisions. [ABSTRACT FROM AUTHOR]