Related papers: Adversarial Scrutiny of Evidentiary Statistical So…

Over recent years, devising classification algorithms that are robust to adversarial perturbations has emerged as a challenging problem. In particular, deep neural nets (DNNs) seem to be susceptible to small imperceptible changes over test…

There has been a recent surge in adversarial attacks on deep learning based automatic speech recognition (ASR) systems. These attacks pose new challenges to deep learning security and have raised significant concerns in deploying ASR…

In the future, powerful AI systems may be deployed in high-stakes settings, where a single failure could be catastrophic. One technique for improving AI safety in high-stakes settings is adversarial training, which uses an adversary to…

Malicious software (malware) is a major cyber threat that has to be tackled with Machine Learning (ML) techniques because millions of new malware examples are injected into cyberspace on a daily basis. However, ML is vulnerable to attacks…

The growing philosophical literature on algorithmic fairness has examined statistical criteria such as equalized odds and calibration, causal and counterfactual approaches, and the role of structural and compounding injustices. Yet an…

Recent studies have highlighted adversarial examples as a ubiquitous threat to different neural network models and many downstream applications. Nonetheless, as unique data properties have inspired distinct and powerful learning principles,…

In this paper, we propose an adversary model to facilitate forensic investigations of mobile devices (e.g. Android, iOS and Windows smartphones) that can be readily adapted to the latest mobile device technologies. This is essential given…

Recently, the problem of robustness of pre-trained language models (PrLMs) has received increasing research interest. Latest studies on adversarial attacks achieve high attack success rates against PrLMs, claiming that PrLMs are not robust.…

Artificial neural networks have been successfully used for many different classification tasks including malware detection and distinguishing between malicious and non-malicious programs. Although artificial neural networks perform very…

Recent works have empirically shown that there exist adversarial examples that can be hidden from neural network interpretability (namely, making network interpretation maps visually similar), or interpretability is itself susceptible to…

Correctly evaluating defenses against adversarial examples has proven to be extremely difficult. Despite the significant amount of recent work attempting to design defenses that withstand adaptive attacks, few have succeeded; most papers…

An intriguing property of deep neural networks is their inherent vulnerability to adversarial inputs, which significantly hinders their application in security-critical domains. Most existing detection methods attempt to use carefully…

Deep learning has undoubtedly offered tremendous improvements in the performance of state-of-the-art speech emotion recognition (SER) systems. However, recent research on adversarial examples poses enormous challenges on the robustness of…

The existence of adversarial examples has led to considerable uncertainty regarding the trust one can justifiably put in predictions produced by automated systems. This uncertainty has, in turn, lead to considerable research effort in…

Pretrained models from self-supervision are prevalently used in fine-tuning downstream tasks faster or for better accuracy. However, gaining robustness from pretraining is left unexplored. We introduce adversarial training into…

Several recent results provide theoretical insights into the phenomena of adversarial examples. Existing results, however, are often limited due to a gap between the simplicity of the models studied and the complexity of those deployed in…

As we rely on machine learning (ML) models to make more consequential decisions, the issue of ML models perpetuating or even exacerbating undesirable historical biases (e.g., gender and racial biases) has come to the fore of the public's…

Adversarial robustness is one of the essential safety criteria for guaranteeing the reliability of machine learning models. While various adversarial robustness testing approaches were introduced in the last decade, we note that most of…

Adversarial attacks can mislead automatic speech recognition (ASR) systems into predicting an arbitrary target text, thus posing a clear security threat. To prevent such attacks, we propose DistriBlock, an efficient detection strategy…

Recently researchers have proposed using deep learning-based systems for malware detection. Unfortunately, all deep learning classification systems are vulnerable to adversarial attacks. Previous work has studied adversarial attacks against…