Search

As usage of military artificial intelligence (AI) expands, so will anti-AI countermeasures, known as adversarials. International humanitarian law offers many protections through its obligations in attack, but the nature of adversarials generates ambiguity regarding which party (system user or opponent) should incur attacker responsibilities. This article offers a cognitive framework for legally analyzing adversarials. It explores the technical, tactical and legal dimensions of adversarials, and proposes a model based on foreseeable harm to determine when legal responsibility should transfer to the countermeasure's author. The article provides illumination to the future combatant who ponders, before putting on their adversarial sunglasses: "Am I conducting an attack?" [ABSTRACT FROM AUTHOR]

This paper tackles the critical challenge of detecting and mitigating unintended political bias in offensive meme detection. Political memes are a powerful tool that can be used to influence public opinion and disrupt voters' mindsets. However, current visual-linguistic models for offensive meme detection exhibit unintended bias and struggle to accurately classify non-offensive and offensive memes. This can harm the fairness of the democratic process either by targeting minority groups or promoting harmful political ideologies. With Hindi being the fifth most spoken language globally and having a significant number of native speakers, it is essential to detect and remove Hindi-based offensive memes to foster a fair and equitable democratic process. To address these concerns, we propose three debiasing techniques to mitigate the overrepresentation of majority group perspectives while addressing the suppression of minority opinions in political discourse. To support our approach, we curate a comprehensive dataset called Pol_Off_Meme, designed especially for the Hindi language. Empirical analysis of this dataset demonstrates the efficacy of our proposed debiasing techniques in reducing political bias in internet memes, promoting a fair and equitable democratic environment. Our debiased model, named D R T I M Att Adv , exhibited superior performance compared to the CLIP-based baseline model. It achieved a significant improvement of +9.72% in the F1-score while reducing the False Positive Rate Difference (FPRD) by -16% and the False Negative Rate Difference (FNRD) by -14.01%. Our efforts strive to cultivate a more informed and inclusive political discourse, ensuring that all opinions, irrespective of their majority or minority status, receive adequate attention and representation. [ABSTRACT FROM AUTHOR]

The article examines the procedural opportunities available to the defense party for evidence collection in Ukraine's criminal process. It is emphasized that despite the declared equality of rights of the parties to collect and submit items, documents, and evidence to the court under Article 22 of the Criminal Procedure Code of Ukraine, during pre-trial investigation, the prosecution party has a number of advantages over the defense party in terms of available means of evidence. The procedural opportunities available to the defense party for evidence collection have been analyzed, comparing them with the actual evidentiary capabilities of the prosecution party. The author underscores that the current Ukrainian criminal procedural legislation contains precedents granting the defense party certain powers traditionally associated with the activities of the prosecution party. It is proposed to grant the defense party, the victim, and the representative of a legal entity, subject to criminal proceedings, the right to perform certain procedural actions during the pre-trial investigation stage, which currently can only be carried out by the prosecution party. According to the author, expanding the evidentiary powers of the listed subjects is possible provided that some principles are adhered to, including verifiability of procedural actions' results, creating no obstacles for the prosecution party, the usefulness of such expansion, and coercion is avoided. The mentioned participants in the criminal proceedings may be granted the opportunity to conduct inspections of computer data, interrogate witnesses and suspects, undergo voluntary inspections of a person (including medical ones), extract data from technical devices and technical means, and so forth. [ABSTRACT FROM AUTHOR]

The investigating judge was first mentioned in the French Code of Criminal Procedure in 1808, and then in other countries, including Russia, where a similar procedural person was called a court investigator and was abolished in the early years of Soviet power. Currently, there is a debate in national jurisprudence about the return of the court investigator, showing the ambiguous attitude to this problem. The purpose of the article is to analyze the current state of legal regulation of the institute of investigating judges in the French criminal procedure legislation in order to determine the effectiveness of the performance of its tasks; as well as the nature of criminal procedure relations between the participants of the French criminal proceedings in comparison to similar national ones. The findings make it possible to present a coherent, logical, time-tested construction of the institution of the investigating judge. These activities are characterized by much more detailed regulation, including in the interests of the defense, with a general focus on the protection of individual rights, the exclusion of accusatory bias and the existence of effective safeguards for this purpose. The article shows the real possibilities of the investigating judge to exercise his autonomy and independence from the prosecutor. At the same time, such regulation is sufficiently effective to achieve an objective approach. Other positive consequences are possible in the form of elements of attorney investigation and the deposit of certain types of evidence.

By establishing the initial legal status of the person held criminally liable as a "state of innocence", the presumption of innocence exerts a substantial influence on the entire criminal process: it determines the direction and rules of the criminal-procedural evidence during the entire process; it conditions and guarantees the inherence of the rights and freedoms of the accused, making it impossible to restrict them in the absence of sufficient grounds and necessities to do so. In the study, on the basis of the analysis of the provisions on the presumption of innocence in criminal proceedings, the opinion that the purpose of criminal procedural evidence is to obtain authentic knowledge of the guilt of the person in committing the crime, i.e. to rebut the presumption of innocence, is justified. This objective can be achieved only if all the circumstances of the case are fully and objectively investigated. The theoretical and practical importance of the study on the impact of the presumption of innocence on the distribution of the burden of proof in criminal proceedings is determined by the interpretation of the current problems of the criminal process, examined from the position of the presumption of innocence as a principle of the criminal process, focused on strengthening the procedural guarantees of the rights and freedoms of the individual. [ABSTRACT FROM AUTHOR]

This article discusses the stability of a two-species ecosystem composed of an ammensal (x) and an adversarial (y) species that are continuously harvested. A mathematical model is defined by a system of two nonlinear ordinary differential equations of first order. The considered system's boundedness is investigated. The local stability of the system is described using a variational matrix, while the global stability is examined using Lyapunov's function. The prerequisite for the system to exist in bionomic equilibrium has been identified. The ideal harvesting technique is determined using the maximal principle proposed by Pontryagin. In MATLAB simulations, the stability of the deterministic system is demonstrated for the specified set of parameters.

The database of faces containing sensitive information is at risk of being targeted by unauthorized automatic recognition systems, which is a significant concern for privacy. Although there are existing methods that aim to conceal identifiable information by adding adversarial perturbations to faces, they suffer from noticeable distortions that significantly compromise visual perception, and therefore, offer limited protection to privacy. Furthermore, the increasing prevalence of appearance anxiety on social media has led to users preferring to beautify their faces before uploading images. In this paper, we design a novel face database protection scheme via beautification with chaotic systems. Specifically, we construct the adversarial face with better visual perception via beautification for each face in the database. In the training, the face matcher and the beautification discriminator are federated against the generator, prompting it to generate beauty-like perturbations on the face to confuse the face matcher. Namely, the pixel changes produced by face beautification mask the adversarial perturbations. Moreover, we use chaotic systems to disrupt the order of adversarial faces in the database, further mitigating the risk of privacy leakage. Our scheme has been extensively evaluated through experiments, which show that it effectively defends against unauthorized attacks while also yielding good visual results. [ABSTRACT FROM AUTHOR]

Generative adversarial networks (GANs) have become increasingly powerful, generating mind-blowing photorealistic images that mimic the content of datasets they have been trained to replicate. One recurrent theme in medical imaging, is whether GANs can also be as effective at generating workable medical data, as they are for generating realistic RGB images. In this paper, we perform a multi-GAN and multi-application study, to gauge the benefits of GANs in medical imaging. We tested various GAN architectures, from basic DCGAN to more sophisticated style-based GANs, on three medical imaging modalities and organs, namely: cardiac cine-MRI, liver CT, and RGB retina images. GANs were trained on well-known and widely utilized datasets, from which their FID scores were computed, to measure the visual acuity of their generated images. We further tested their usefulness by measuring the segmentation accuracy of a U-Net trained on these generated images and the original data. The results reveal that GANs are far from being equal, as some are ill-suited for medical imaging applications, while others performed much better. The top-performing GANs are capable of generating realistic-looking medical images by FID standards, that can fool trained experts in a visual Turing test and comply to some metrics. However, segmentation results suggest that no GAN is capable of reproducing the full richness of medical datasets. [ABSTRACT FROM AUTHOR]

Classical strategy as a concept encompasses two different logics (instrumentality and adversariality) as well as two different modes (decision-making and performance). In modern strategy, these modes have been on diverging paths, with varying interpretations privileging one logic above the other. Game theory focuses on decision-making, but encompasses both adversariality and instrumentality. Operational art focuses on performance, but in an adversarial context. The ends, ways, means model emphasises performance in an instrumental context. Each is imbalanced and inadequate when faced with the challenge of comprehending and controlling war. Strategic studies must make a return to balanced interpretations of strategy. [ABSTRACT FROM AUTHOR]

This article examines the concept of defense disclosures within the theory of managerialism in criminal proceedings in Ghana. Through a doctrinal and comparative legal analysis with the English jurisdiction, it finds that in substance, the requirement of defense disclosure seeks to move the criminal process from its core protectionist ideology that insulates the accused from matters of proof toward a managerial process informed by objectives of truth-finding, trial efficiency and case management. Ironically, this new direction in the criminal trial process is in practice denounced as being at odds with the procedural due process values that shield the accused from matters of proof and pretrial disclosures. The problem is that unlike in England where the move towards defense disclosures is informed by a clear policy change, the managerial policy introduced by the Judiciary in Ghana is not grounded in any articulated theory or policy direction. While pursuing a path of ensuring effective criminal adjudication through mutual disclosures by the parties, it is important to find a proper balance between the denounced but yet adopted procedural concept of defense disclosures and the highly valued protectionist rights of the accused.

Social media platforms have grown in importance as sources of information and as a complement to traditional media. If informative and relevant tweets on social media platforms can be effectively detected and analyzed during crisis events, it will help humanitarian organizations with situational awareness and planning relief activities. In this work, we propose an adversarial multimodal auto-encoder model for detecting and analyzing crisis-related tweets, which analyzes the complex multimodal content of tweets and integrates adversarial strategies to generate a joint representation containing information from multiple sources. Through extensive experiments on real datasets, we demonstrate the superior performance of the proposed model. [ABSTRACT FROM AUTHOR]

Autism Spectrum Disorder (ASD) requires a precise diagnosis in order to be managed and rehabilitated. Non-invasive neuroimaging methods are disease markers that can be used to help diagnose ASD. The majority of available techniques in the literature use functional magnetic resonance imaging (fMRI) to detect ASD with a small dataset, resulting in high accuracy but low generality. Traditional supervised machine learning classification algorithms such as support vector machines function well with unstructured and semi structured data such as text, images, and videos, but their performance and robustness are restricted by the size of the accompanying training data. Deep learning on the other hand creates an artificial neural network that can learn and make intelligent judgments on its own by layering algorithms. It takes use of plentiful low-cost computing and many approaches are focused with very big datasets that are concerned with creating far larger and more sophisticated neural networks. Generative modelling, also known as Generative Adversarial Networks (GANs), is an unsupervised deep learning task that entails automatically discovering and learning regularities or patterns in input data in order for the model to generate or output new examples that could have been drawn from the original dataset. GANs are an exciting and rapidly changing field that delivers on the promise of generative models in terms of their ability to generate realistic examples across a range of problem domains, most notably in image-to-image translation tasks and hasn't been explored much for Autism spectrum disorder prediction in the past. In this paper, we present a novel conditional generative adversarial network, or cGAN for short, which is a form of GAN that uses a generator model to conditionally generate images. In terms of prediction and accuracy, they outperform the standard GAN. The proposed model is 74% more accurate than the traditional methods and takes only around 10 min for training even with a huge dataset. [ABSTRACT FROM AUTHOR]

Learning-based translation between MRI contrasts involves supervised deep models trained using high-quality source- and target-contrast images derived from fully-sampled acquisitions, which might be difficult to collect under limitations on scan costs or time. To facilitate curation of training sets, here we introduce the first semi-supervised model for MRI contrast translation (ssGAN) that can be trained directly using undersampled k-space data. To enable semi-supervised learning on undersampled data, ssGAN introduces novel multi-coil losses in image, k-space, and adversarial domains. The multi-coil losses are selectively enforced on acquired k-space samples unlike traditional losses in single-coil synthesis models. Comprehensive experiments on retrospectively undersampled multi-contrast brain MRI datasets are provided. Our results demonstrate that ssGAN yields on par performance to a supervised model, while outperforming single-coil models trained on coil-combined magnitude images. It also outperforms cascaded reconstruction-synthesis models where a supervised synthesis model is trained following self-supervised reconstruction of undersampled data. Thus, ssGAN holds great promise to improve the feasibility of learning-based multi-contrast MRI synthesis. [ABSTRACT FROM AUTHOR]

This article discusses the stability of a two-species ecosystem composed of an ammensal (x) and an adversarial (y) species that are continuously harvested. A mathematical model is defined by a system of two nonlinear ordinary differential equations of first order. The considered system's boundedness is investigated. The local stability of the system is described using a variational matrix, while the global stability is examined using Lyapunov's function. The prerequisite for the system to exist in bionomic equilibrium has been identified. The ideal harvesting technique is determined using the maximal principle proposed by Pontryagin. In MATLAB simulations, the stability of the deterministic system is demonstrated for the specified set of parameters. [ABSTRACT FROM AUTHOR]

Craniomaxillofacial defects caused by congenital or acquired reasons seriously affect patients' physical and mental health. How to accurately and objectively repair the morphology of craniomaxillofacial tissues and organs through surgery is a difficult problem, and the preoperative virtual design is crucial. Traditional preoperative virtual design methods include mirror technology, statistical shape model, and deformable template. However, these methods are complex, time‐consuming, and only applicable to some types of defects. Therefore, a general, intelligent, and personalized craniomaxillofacial defect virtual reconstruction system is desired. To solve this problem, a novel deep learning method, RecGAN, is proposed in this paper. RecGAN can learn the bone morphology of normal people, repair the defect intelligently based on the patient's remaining bone, and fully adapt to the special conditions of different patients. Currently, there are no open‐source maxillofacial data sets available. Thus, a new maxillofacial computed tomography image data set with 500 simulated cases and 100 clinical cases is constructed to train and validate the method. The experimental results show that RecGAN can effectively restore the normal bone and tissue morphology of the patient's craniomaxillofacial defect area, solve the problem that there is no objective repair method for craniomaxillofacial defect, and achieve the best effect in the same type of research. The proposed intelligent craniomaxillofacial defect virtual reconstruction system based on RecGAN is expected to be applied in future clinical practice. [ABSTRACT FROM AUTHOR]

True-color imagery of satellites provides various atmospheric and surface information for intuitive understanding and visualization. This article presents a conditional generative adversarial network method for generating daytime and nighttime hypothetical visible (VIS) bands of the advanced meteorological imager (AMI) sensor onboard the geostationary Korea multipurpose satellite. The AMI datasets in the form of albedo and brightness temperature (${{\boldsymbol{T}}}_{\boldsymbol{B}}$) were normalized and denormalized between 0 and 1 data-to-data (D2D) translation. The D2D model was trained and tested using data pair of the albedos at AMI VIS bands and AMI infrared (IR) bands or ${{\boldsymbol{T}}}_{\boldsymbol{B}}$ differences between two AMI IR bands. The constructed D2D model showed that the statistical results of bias, root-mean-square-error, and correlation coefficient between the observed and D2D-generated AMI VIS bands during daytime were −0.006 and 0.047 in albedo, and 0.941 for the blue band; −0.007 and 0.05 in albedo and 0.939 for the green band; −0.01 and 0.061 in albedo, and 0.917 for the red band, respectively. The proposed D2D method is being officially used by the Korea meteorological administration. Except for simulating desert areas as clouds at night, the D2D model demonstrated excellent performance, generating hypothetical AMI VIS bands at day and night. Consequently, this article could significantly contribute to the monitoring and understanding of meteorological phenomena over one-third of the Earth. Additionally, the method can be extended to other geostationary weather satellites, including Himawari-8, Fengyun-4A, meteosat third generation, and geostationary operational environmental satellites.

Generative adversarial models with convolutional neural network (CNN) backbones have recently been established as state-of-the-art in numerous medical image synthesis tasks. However, CNNs are designed to perform local processing with compact filters, and this inductive bias compromises learning of contextual features. Here, we propose a novel generative adversarial approach for medical image synthesis, ResViT, that leverages the contextual sensitivity of vision transformers along with the precision of convolution operators and realism of adversarial learning. ResViT’s generator employs a central bottleneck comprising novel aggregated residual transformer (ART) blocks that synergistically combine residual convolutional and transformer modules. Residual connections in ART blocks promote diversity in captured representations, while a channel compression module distills task-relevant information. A weight sharing strategy is introduced among ART blocks to mitigate computational burden. A unified implementation is introduced to avoid the need to rebuild separate synthesis models for varying source-target modality configurations. Comprehensive demonstrations are performed for synthesizing missing sequences in multi-contrast MRI, and CT images from MRI. Our results indicate superiority of ResViT against competing CNN- and transformer-based methods in terms of qualitative observations and quantitative metrics. [ABSTRACT FROM AUTHOR]

Identification of a heterogeneous conductivity field and reconstruction of a contaminant release history are key aspects of subsurface remediation. These two goals are achieved by combining model predictions with sparse and noisy hydraulic head and concentration measurements. Solution of this inverse problem is notoriously difficult due to, in part, high dimensionality of the parameter space and high computational cost of repeated forward solves. We use a convolutional adversarial autoencoder (CAAE) to parameterize a heterogeneous non‐Gaussian conductivity field via a low‐dimensional latent representation. A three‐dimensional dense convolutional encoder‐decoder (DenseED) network serves as a forward surrogate of the flow and transport model. The CAAE‐DenseED surrogate is fed into the ensemble smoother with multiple data assimilation (ESMDA) algorithm to sample from the Bayesian posterior distribution of the unknown parameters, forming a CAAE‐DenseED‐ESMDA inversion framework. The resulting CAAE‐DenseED‐ESMDA inversion strategy is used to identify a three‐dimensional contaminant source and conductivity field. A comparison of the inversion results from CAAE‐ESMDA with physical flow and transport simulator and from CAAE‐DenseED‐ESMDA shows that the latter yields accurate reconstruction results at the fraction of the computational cost of the former. Plain Language Summary: Identification of a heterogeneous conductivity field and reconstruction of a contaminant release history are key aspects of subsurface remediation. These two goals are achieved by combining model predictions with sparse and noisy hydraulic head and concentration measurements. Solution of this inverse problem is notoriously difficult due to, in part, high dimensionality of the parameter space and high computational cost of repeated forward solves. We develop a deep‐learning strategy to identify a three‐dimensional contaminant source and conductivity field from sparse observations. Key Points: Our deep‐learning strategy reconstructs three‐dimensional conductivity field and contaminant release historyConductivity parameterization with convolutional adversarial autoencoder reduces the inverse problem's dimensionalityConvolutional encoder‐decoder acts as a surrogate of forward models; ensemble smoother approximates parameters' posterior distribution [ABSTRACT FROM AUTHOR]

The level of realization of the right to a fair trial is one of the crucial indicators of democracy in any state. In order to ensure this right, all the minimum standards deriving from it must be clearly understood by law enforcement agencies and their practice must meet these standards. As equality of arms, the right to a fair trial, is not directly enshrined in the text of Article 6 of the European Convention on Human Rights (hereafter - the Convention) and is of implicit character; the issues like its essence, content and the way it should manifest in practice are open for discussion. For this reason, the focus on those issues is highly relevant. The aim of this article is, with reference to the case law of the European Court of Human Rights (hereafter - ECHR) and the modern doctrine based on this right, to explain the role of this principle and the essence of its mutual relations with the other elements of the right to a fair trial. Selected case law of ECHR bears great interest compared with other decisions and is discussed in the form of empirical materials of the study. From the doctrinal materials, interpretation of Article 6 of the Convention and theoretical sources related to the European standards in the criminal procedure are also analyzed. The article exercises methods of dialectical comprehension; they are determinism, induction, deduction, case studies and methods of law interpretation. As a result of the study, a unique doctrinal commentary has been obtained in the context of adversariality and impartial and independent court principles of the concept of equality of arms, as well as, interaction of the minimum rights of persons subject to criminal prosecution, guaranteed by the Convention.

Supervised reconstruction models are characteristically trained on matched pairs of undersampled and fully-sampled data to capture an MRI prior, along with supervision regarding the imaging operator to enforce data consistency. To reduce supervision requirements, the recent deep image prior framework instead conjoins untrained MRI priors with the imaging operator during inference. Yet, canonical convolutional architectures are suboptimal in capturing long-range relationships, and priors based on randomly initialized networks may yield suboptimal performance. To address these limitations, here we introduce a novel unsupervised MRI reconstruction method based on zero-Shot Learned Adversarial TransformERs (SLATER). SLATER embodies a deep adversarial network with cross-attention transformers to map noise and latent variables onto coil-combined MR images. During pre-training, this unconditional network learns a high-quality MRI prior in an unsupervised generative modeling task. During inference, a zero-shot reconstruction is then performed by incorporating the imaging operator and optimizing the prior to maximize consistency to undersampled data. Comprehensive experiments on brain MRI datasets clearly demonstrate the superior performance of SLATER against state-of-the-art unsupervised methods. [ABSTRACT FROM AUTHOR]

Adversarial attacks have been demonstrated to fool the deep classification networks. There are two key characteristics of these attacks: firstly, these perturbations are mostly additive noises carefully crafted from the deep neural network itself. Secondly, the noises are added to the whole image, not considering them as the combination of multiple components from which they are made. Motivated by these observations, in this research, we first study the role of various image components and the impact of these components on the classification of the images. These manipulations do not require the knowledge of the networks and external noise to function effectively and hence have the potential to be one of the most practical options for real-world attacks. Based on the significance of the particular image components, we also propose a transferable adversarial attack against unseen deep networks. The proposed attack utilizes the projected gradient descent strategy to add the adversarial perturbation to the manipulated component image. The experiments are conducted on a wide range of networks and four databases including ImageNet and CIFAR-100. The experiments show that the proposed attack achieved better transferability and hence gives an upper hand to an attacker. On the ImageNet database, the success rate of the proposed attack is up to 88.5%, while the current state-of-the-art attack success rate on the database is 53.8%. We have further tested the resiliency of the attack against one of the most successful defenses namely adversarial training to measure its strength. The comparison with several challenging attacks shows that: (i) the proposed attack has a higher transferability rate against multiple unseen networks and (ii) it is hard to mitigate its impact. We claim that based on the understanding of the image components, the proposed research has been able to identify a newer adversarial attack unseen so far and unsolvable using the current defense mechanisms. [ABSTRACT FROM AUTHOR]

Although deep learning technologies have been widely exploited in many fields, they are vulnerable to adversarial attacks by adding small perturbations to legitimate inputs to fool targeted models. However, few studies have focused on intelligent networking in such an adversarial environment, which can pose serious security threats. In fact, while challenging intelligent networking, adversarial environments also bring about opportunities. In this paper, we, for the first time, simultaneously analyze the challenges and opportunities that the adversarial environment brings to intelligent networking. Specifically, we focus on challenges that the adversarial environment will pose on the existing intelligent networking. Furthermore, we investigate frameworks and approaches that combine adversarial machine learning with intelligent networking to solve the existing deficiencies of intelligent networking. Finally, we summarize the issues, including opportunities and challenges, which can allow researchers to focus on intelligent networking in adversarial environments. [ABSTRACT FROM AUTHOR]

• We propose to use the TA attention module to capture the relationship of different video clips. • We introduce an adversarial loss to ensure the stability and effectiveness to learn the model. • Our method achieves a competitive action evaluation result on the MTL-AQA dataset. Action quality assessment (AQA) is a task to assess the performance of a human action, which can be widely used in many real-world scenarios such as sport events. Current AQA methods generally extract features from the video and perform regression analysis to obtain the action quality score. In this process, aggregated video features may not reflect different stages of an action, which are important to evaluate an action is good or not. To address this issue, we propose to divide the video into different clips and learn the relationship between them, which may capture the action changes for accurate assessment. Time-aware (TA) attention mechanism is used to evaluate this relationship. In the experiment, our proposed method achieves promising results on the MTL-AQA dataset compared with existing AQA methods. [ABSTRACT FROM AUTHOR]

We consider optimal transport-based distributionally robust optimization (DRO) problems with locally strongly convex transport cost functions and affine decision rules. Under conventional convexity assumptions on the underlying loss function, we obtain structural results about the value function, the optimal policy, and the worst-case optimal transport adversarial model. These results expose a rich structure embedded in the DRO problem (e.g., strong convexity even if the non-DRO problem is not strongly convex, a suitable scaling of the Lagrangian for the DRO constraint, etc., which are crucial for the design of efficient algorithms). As a consequence of these results, one can develop efficient optimization procedures that have the same sample and iteration complexity as a natural non-DRO benchmark algorithm, such as stochastic gradient descent. [ABSTRACT FROM AUTHOR]

As the internet continues to be populated with new devices and emerging technologies, the attack surface grows exponentially. Technology is shifting towards a profit-driven Internet of Things market where security is an afterthought. Traditional defending approaches are no longer sufficient to detect both known and unknown attacks to high accuracy. Machine learning intrusion detection systems have proven their success in identifying unknown attacks with high precision. Nevertheless, machine learning models are also vulnerable to attacks. Adversarial examples can be used to evaluate the robustness of a designed model before it is deployed. Further, using adversarial examples is critical to creating a robust model designed for an adversarial environment. Our work evaluates both traditional machine learning and deep learning models’ robustness using the Bot-IoT dataset. Our methodology included two main approaches. First, label poisoning, used to cause incorrect classification by the model. Second, the fast gradient sign method, used to evade detection measures. The experiments demonstrated that an attacker could manipulate or circumvent detection with significant probability.

• Classifying time series with Euclidean distance is robust against adversarial attacks. • Time series classifiers using fixed kernels are robust against adversarial attacks. • This is empirically proven on 85 datasets for 2 state-of-the-art adversarial attacks. Deep neural networks have been shown to be vulnerable against specifically-crafted perturbations designed to affect their predictive performance. Such perturbations, formally termed 'adversarial attacks' have been designed for various domains in the literature, most prominently in computer vision and more recently, in time series classification. Therefore there is a need to derive robust strategies to defend deep networks from such attacks. In this work we propose to establish axioms of robustness against adversarial attacks in time series classification. We subsequently design a suitable experimental methodology and empirically validate the hypotheses put forth. Results obtained from our investigations confirm the proposed hypotheses, and provide a strong empirical baseline with a view to mitigating the effects of adversarial attacks in deep time series classification. [ABSTRACT FROM AUTHOR]

Abstract Fair classification has become an important topic in machine learning research. While most bias mitigation strategies focus on neural networks, we noticed a lack of work on fair classifiers based on decision trees even though they have proven very efficient. In an up-to-date comparison of state-of-the-art classification algorithms in tabular data, tree boosting outperforms deep learning (Zhang et al. in Expert Syst Appl 82:128–150, 2017). For this reason, we have developed a novel approach of adversarial gradient tree boosting. The objective of the algorithm is to predict the output Y with gradient tree boosting while minimizing the ability of an adversarial neural network to predict the sensitive attribute S. The approach incorporates at each iteration the gradient of the neural network directly in the gradient tree boosting. We empirically assess our approach on four popular data sets and compare against state-of-the-art algorithms. The results show that our algorithm achieves a higher accuracy while obtaining the same level of fairness, as measured using a set of different common fairness definitions.

In the long-term deployment of mobile robots, changing appearance brings challenges for localization. When a robot travels to the same place or restarts from an existing map, global localization is needed, where place recognition provides coarse position information. For visual sensors, changing appearances such as the transition from day to night and seasonal variation can reduce the performance of a visual place recognition system. To address this problem, we propose to learn domain-unrelated features across extreme changing appearance, where a domain denotes a specific appearance condition, such as a season or a kind of weather. We use an adversarial network with two discriminators to disentangle domain-related features and domain-unrelated features from images, and the domain-unrelated features are used as descriptors in place recognition. Provided images from different domains, our network is trained in a self-supervised manner which does not require correspondences between these domains. Besides, our feature extractors are shared among all domains, making it possible to contain more appearance without increasing model complexity. Qualitative and quantitative results on two toy cases are presented to show that our network can disentangle domain-related and domain-unrelated features from given data. Experiments on three public datasets and one proposed dataset for visual place recognition are conducted to illustrate the performance of our method compared with several typical algorithms. Besides, an ablation study is designed to validate the effectiveness of the introduced discriminators in our network. Additionally, we use a four-domain dataset to verify that the network can extend to multiple domains with one model while achieving similar performance. [ABSTRACT FROM AUTHOR]

Automatic speech emotion recognition provides computers with critical context to enable user understanding. While methods trained and tested within the same dataset have been shown successful, they often fail when applied to unseen datasets. To address this, recent work has focused on adversarial methods to find more generalized representations of emotional speech. However, many of these methods have issues converging, and only involve datasets collected in laboratory conditions. In this paper, we introduce Adversarial Discriminative Domain Generalization (ADDoG), which follows an easier to train “meet in the middle” approach. The model iteratively moves representations learned for each dataset closer to one another, improving cross-dataset generalization. We also introduce Multiclass ADDoG, or MADDoG, which is able to extend the proposed method to more than two datasets, simultaneously. Our results show consistent convergence for the introduced methods, with significantly improved results when not using labels from the target dataset. We also show how, in most cases, ADDoG and MADDoG can be used to improve upon baseline state-of-the-art methods when target dataset labels are added and in-the-wild data are considered. Even though our experiments focus on cross-corpus speech emotion, these methods could be used to remove unwanted factors of variation in other settings. [ABSTRACT FROM AUTHOR]

We introduce SPLASH units, a class of learnable activation functions shown to simultaneously improve the accuracy of deep neural networks while also improving their robustness to adversarial attacks. SPLASH units have both a simple parameterization and maintain the ability to approximate a wide range of non-linear functions. SPLASH units are: (1) continuous; (2) grounded (f (0) = 0); (3) use symmetric hinges; and (4) their hinges are placed at fixed locations which are derived from the data (i.e. no learning required). Compared to nine other learned and fixed activation functions, including ReLU and its variants, SPLASH units show superior performance across three datasets (MNIST, CIFAR-10, and CIFAR-100) and four architectures (LeNet5, All-CNN, ResNet-20, and Network-in-Network). Furthermore, we show that SPLASH units significantly increase the robustness of deep neural networks to adversarial attacks. Our experiments on both black-box and white-box adversarial attacks show that commonly-used architectures, namely LeNet5, All-CNN, Network-in-Network, and ResNet-20, can be up to 31% more robust to adversarial attacks by simply using SPLASH units instead of ReLUs. Finally, we show the benefits of using SPLASH activation functions in bigger architectures designed for non-trivial datasets such as ImageNet. [ABSTRACT FROM AUTHOR]

Deep Learning-based fault diagnosis has aroused widespread attention in machine fault diagnosis. Helicopter is an important transport for its special purpose. How to ensure its normal operation is a challenging task. Nevertheless, the existing research mainly focuses on single bearing or gear of gearbox, while there are few reports about intelligent fault diagnosis of bearing and shaft in helicopter transmission system. Furthermore, traditional domain adaption-based fault diagnosis methods assume that the source machine and target machine have the same class distribution. Besides, the latent distributed feature of target domain data is rarely developed, and the distributional discrepancy of shared-class samples during domain adaption with outlier class is rarely considered. To address these issues, we propose a domain distribution variation learning (DDVL) via adversarial adaption for helicopter transmission system fault diagnosis in this paper. Hereinto, the distributional discrepancy of partial shared-class is measured by adversarial training during open-set domain adaption. Especially, a self-supervised learning framework via the pseudo-label and weight normalization is proposed to develop the latent distribution feature of target data with unknown labels. The case study from a simulated helicopter transmission system is used to verify the effectiveness of DDVL. Our method outperforms other comparison methods in different case studies for helicopter transmission system fault diagnosis. [ABSTRACT FROM AUTHOR]

This paper presents a client/server privacy-preserving network in the context of multicentric medical image analysis. Our approach is based on adversarial learning which encodes images to obfuscate the patient identity while preserving enough information for a target task. Our novel architecture is composed of three components: 1) an encoder network which removes identity-specific features from input medical images, 2) a discriminator network that attempts to identify the subject from the encoded images, 3) a medical image analysis network which analyzes the content of the encoded images (segmentation in our case). By simultaneously fooling the discriminator and optimizing the medical analysis network, the encoder learns to remove privacy-specific features while keeping those essentials for the target task. Our approach is illustrated on the problem of segmenting brain MRI from the large-scale Parkinson Progression Marker Initiative (PPMI) dataset. Using longitudinal data from PPMI, we show that the discriminator learns to heavily distort input images while allowing for highly accurate segmentation results. Our results also demonstrate that an encoder trained on the PPMI dataset can be used for segmenting other datasets, without the need for retraining. The code is made available at: https://github.com/bachkimn/Privacy-Net-An-Adversarial-Approach-forIdentity-Obfuscated-Segmentation-of-MedicalImages [ABSTRACT FROM AUTHOR]

A smart contract honeypot is a special type of smart contract. This type of contract seems to have obvious vulnerabilities in contract design. If a user transfers a certain amount of funds to the contract, then the user can withdraw the funds in the contract. However, once users try to take advantage of this seemingly obvious vulnerability, they will fall into a real trap. Consequently, the user's investment in the contract cannot be retrieved. The honeypot induces other accounts to launch funds, which seriously threatens the security of property on the blockchain. Detection methods for honeypots are available. However, studying the manner by which to defend existing honeypots is insufficient to fight against honeypots. The new honeypots that may appear in the future from the perspective of an attacker must also be predicted. Therefore, we propose a type of adversarial honeypot. The code and behavioral features of honeypots are obtained through a comparative analysis of the 158,568 nonhoneypots and 352 honeypots. To build an adversarial honeypot, we try to separately hide these features andmake the honeypot bypass the existing detection technology. We construct 18 instances on the basis of the proposed adversarial honeypot and use an open-source honeypot detection tool to detect these instances. The experimental result shows that the proposed honeypot can bypass the detection tool with a 100% ratio. Therefore, this type of honeypot should be given attention, and defensive measures should be proposed as soon as possible. [ABSTRACT FROM AUTHOR]

In the article, the author deals with the issue of adversariality of criminal proceedings as one of the basic principles of criminal proceedings with a focus on the application of this principle in criminal proceedings. In the article, the author focused on clarifying the concept of adversariality, and followed up on the general definition of adversariality as a principle of criminal procedure. Given that this is a category of broad importance, the author tried to define these definitions as precisely as possible and did not focus on its comparison with other principles of criminal proceedings, but focused only on the principle of adversariality. Furthermore, in the article, the author focused on the application of the adversarial principle in selected post-clerical acts of criminal proceedings with a focus on the exercise of the rights of the accused and exceptions to the principle of adversariality in preparatory proceedings. In the article, the author deals with the issue of adversariality of criminal proceedings as one of the basic principles of criminal proceedings with a focus on the application of this principle in criminal proceedings. In the article, the author focused on clarifying the concept of adversariality, and followed up on the general definition of adversariality as a principle of criminal procedure. Given that this is a category of broad meaning, the author tried to define these definitions as precisely as possible and did not focus on its comparison with other principles of criminal proceed-ings, but focused only on the principle of adversariality. Furthermore, in the article, the author focused on the applica-tion of the adversarial principle in selected post-clerical acts of criminal proceedings with a focus on the exercise of the rights of the accused and exceptions to the principle of adversariality in preparatory proceedings. Attention is also paid to the violation of the principle of contradictory in the preparatory proceedings in the fourth chapter. [ABSTRACT FROM AUTHOR]

Explaining cases of stopping and dropping the litigation and their reasons in the Jordanian Code of Procedure, the problematic of this study is to explain the stopping of the Jordanian legislator from cases of stopping and dropping the litigation and the adequacy of the legal texts regulating it in Jordanian legislation. The two researchers followed the descriptive and analytical approach in analyzing legal texts, particularly the texts of the Jordanian Code of Civil Procedure, the jurisprudence, and the opinions of the jurists. Likewise, the comparative approach, whenever necessary, in order to enrich the study, and the researchers reached a number of findings and recommendations, and the most important result was: that the litigation may be intercepted by situations that lead to affecting the course of its outcome, such as endowment and omission. The researchers recommended the necessity of expanding the study of the judicial litigation and what influences it in the cases of stopping and abrogation, due to its importance in determining the legal positions of the parties. [ABSTRACT FROM AUTHOR]

Recent studies have shown that state-of-the-art DNNs are not always credible, despite their impressive performance on the hold-out test set of a variety of tasks. These models tend to exploit dataset shortcuts to make predictions, rather than learn the underlying task. The non-credibility could lead to low generalization, adversarial vulnerability, as well as algorithmic discrimination of the DNN models. In this paper, we propose CREX in order to develop more credible DNNs. The high-level idea of CREX is to encourage DNN models to focus more on evidences that actually matter for the task at hand and to avoid overfitting to data-dependent shortcuts. Specifically, in the DNN training process, CREX directly regularizes the local explanation with expert rationales, i.e., a subset of features highlighted by domain experts as justifications for predictions, to enforce the alignment between local explanations and rationales. Even when rationales are not available, CREX still could be useful by requiring the generated explanations to be sparse. In addition, CREX is widely applicable to different network architectures, including CNN, LSTM and attention model. Experimental results on several text classification datasets demonstrate that CREX could increase the credibility of DNNs. Comprehensive analysis further shows three meaningful improvements of CREX: (1) it significantly increases DNN accuracy on new and previously unseen data beyond test set, (2) it enhances fairness of DNNs in terms of equality of opportunity metric and reduce models' discrimination toward certain demographic group, and (3) it promotes the robustness of DNN models with respect to adversarial attack. These experimental results highlight the advantages of the increased credibility by CREX. [ABSTRACT FROM AUTHOR]

We derive an algorithm that achieves the optimal (within constants) pseudo-regret in both adversarial and stochastic multi-armed bandits without prior knowledge of the regime and time horizon.1 The algorithm is based on online mirror descent (OMD) with Tsallis entropy regularization with power = 1=2 and reduced-variance loss estimators. More generally, we define an adversarial regime with a self-bounding constraint, which includes stochastic regime, stochastically constrained adversarial regime (Wei and Luo, 2018), and stochastic regime with adversarial corruptions (Lykouris et al., 2018) as special cases, and show that the algorithm achieves logarithmic regret guarantee in this regime and all of its special cases simultaneously with the optimal regret guarantee in the adversarial regime. The algorithm also achieves adversarial and stochastic optimality in the utility-based dueling bandit setting. We provide empirical evaluation of the algorithm demonstrating that it significantly outperforms Ucb1 and Exp3 in stochastic environments. We also provide examples of adversarial environments, where Ucb1 and Thompson Sampling exhibit almost linear regret, whereas our algorithm suers only logarithmic regret. To the best of our knowledge, this is the first example demonstrating vulnerability of Thompson Sampling in adversarial environments. Last but not least, we present a general stochastic analysis and a general adversarial analysis of OMD algorithms with Tsallis entropy regularization for 2 [0; 1] and explain the reason why = 1=2 works best. [ABSTRACT FROM AUTHOR]

• A modality invariant adversarial mechanism for improving the multi-style Re-ID task. • Two new datasets from virtuality to reality for the multi-style Re-ID task. • Space transformation and different category classifiers for performance improvement. Person re-identification based on multi-style images helps in crime scene investigation, where only a virtual image (sketch or portrait) of the suspect is available for retrieving possible identities. However, due to the modality gap between multi-style images, standard model of person re-identification cannot achieve satisfactory performance when directly applied to match the virtual images with the real photographs. To address this problem, we propose a modality invariant adversarial mechanism (MIAM) to remove the modality gap between multi-style images. Specifically, the MIAN consists of two parts: a space transformation module to transfer the multi-style person images to a modality-invariant space, and an adversarial learning module "played" between the category classifier and modality classifier to steer the representation learning. The modality classifier discriminates between the real and virtual images while the category classifier predicts the identities of the input transformed images. We explore the space transformation for data augmentation to further bridge the modality gap and facilitate the performance. Furthermore, we build two new datasets for the multi-style Re-ID to evaluate the performance. Extensive experimental results demonstrate the effectiveness of the proposed method on improving the performance against the existing feature learning networks. Further comparison results conducted on different modules in MIAM show that our approach is of favorable generalization ability on alleviating the modality gap to improve the multi-style Re-ID. [ABSTRACT FROM AUTHOR]

This paper addresses the problem of semi-supervised transfer learning with limited cross-modality data in remote sensing. A large amount of multi-modal earth observation images, such as multispectral imagery (MSI) or synthetic aperture radar (SAR) data, are openly available on a global scale, enabling parsing global urban scenes through remote sensing imagery. However, their ability in identifying materials (pixel-wise classification) remains limited, due to the noisy collection environment and poor discriminative information as well as limited number of well-annotated training images. To this end, we propose a novel cross-modal deep-learning framework, called X-ModalNet, with three well-designed modules: self-adversarial module, interactive learning module, and label propagation module, by learning to transfer more discriminative information from a small-scale hyperspectral image (HSI) into the classification task using a large-scale MSI or SAR data. Significantly, X-ModalNet generalizes well, owing to propagating labels on an updatable graph constructed by high-level features on the top of the network, yielding semi-supervised cross-modality learning. We evaluate X-ModalNet on two multi-modal remote sensing datasets (HSI-MSI and HSI-SAR) and achieve a significant improvement in comparison with several state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Owing to the advantages of low storage cost and high query efficiency, cross-modal hashing has received increasing attention recently. As failing to bridge the inherent modality gap between modalities, most existing cross-modal hashing methods have limited capability to explore the semantic consistency information between different modality data, leading to unsatisfactory search performance. To address this problem, we propose a novel deep hashing method named Multi-Task Consistency-Preserving Adversarial Hashing (CPAH) to fully explore the semantic consistency and correlation between different modalities for efficient cross-modal retrieval. First, we design a consistency refined module (CR) to divide the representations of different modality into two irrelevant parts, i.e., modality-common and modality-private representations. Then, a multi-task adversarial learning module (MA) is presented, which can make the modality-common representation of different modalities close to each other on feature distribution and semantic consistency. Finally, the compact and powerful hash codes can be generated from modality-common representation. Comprehensive evaluations conducted on three representative cross-modal benchmark datasets illustrate our method is superior to the state-of-the-art cross-modal hashing methods. [ABSTRACT FROM AUTHOR]

Fair classification has become an important topic in machine learning research. While most bias mitigation strategies focus on neural networks, we noticed a lack of work on fair classifiers based on decision trees even though they have proven very efficient. In an up-to-date comparison of state-of-the-art classification algorithms in tabular data, tree boosting outperforms deep learning (Zhang et al. in Expert Syst Appl 82:128–150, 2017). For this reason, we have developed a novel approach of adversarial gradient tree boosting. The objective of the algorithm is to predict the output Y with gradient tree boosting while minimizing the ability of an adversarial neural network to predict the sensitive attribute S. The approach incorporates at each iteration the gradient of the neural network directly in the gradient tree boosting. We empirically assess our approach on four popular data sets and compare against state-of-the-art algorithms. The results show that our algorithm achieves a higher accuracy while obtaining the same level of fairness, as measured using a set of different common fairness definitions. [ABSTRACT FROM AUTHOR]

Compared to facial expression recognition, expression synthesis requires a very high-dimensional mapping. This problem exacerbates with increasing image sizes and limits existing expression synthesis approaches to relatively small images. We observe that facial expressions often constitute sparsely distributed and locally correlated changes from one expression to another. By exploiting this observation, the number of parameters in an expression synthesis model can be significantly reduced. Therefore, we propose a constrained version of ridge regression that exploits the local and sparse structure of facial expressions. We consider this model as masked regression for learning local receptive fields. In contrast to the existing approaches, our proposed model can be efficiently trained on larger image sizes. Experiments using three publicly available datasets demonstrate that our model is significantly better than ℓ 0 , ℓ 1 and ℓ 2 -regression, SVD based approaches, and kernelized regression in terms of mean-squared-error, visual quality as well as computational and spatial complexities. The reduction in the number of parameters allows our method to generalize better even after training on smaller datasets. The proposed algorithm is also compared with state-of-the-art GANs including Pix2Pix, CycleGAN, StarGAN and GANimation. These GANs produce photo-realistic results as long as the testing and the training distributions are similar. In contrast, our results demonstrate significant generalization of the proposed algorithm over out-of-dataset human photographs, pencil sketches and even animal faces. [ABSTRACT FROM AUTHOR]