相关论文: HopSkipJumpAttack: A Query-Efficient Decision-Base…

We consider the problem of contextual bandits and imitation learning, where the learner lacks direct knowledge of the executed action's reward. Instead, the learner can actively query an expert at each round to compare two actions and…

Solving for adversarial examples with projected gradient descent has been demonstrated to be highly effective in fooling the neural network based classifiers. However, in the black-box setting, the attacker is limited only to the query…

In targeted adversarial attacks on vision models, the selection of the target label is a critical yet often overlooked determinant of attack success. This target label corresponds to the class that the attacker aims to force the model to…

Being an emerging class of in-memory computing architecture, brain-inspired hyperdimensional computing (HDC) mimics brain cognition and leverages random hypervectors (i.e., vectors with a dimensionality of thousands or even more) to…

Deep neural networks remain highly vulnerable to adversarial examples, and most defenses collapse once gradients can be reliably estimated. We identify \emph{gradient consensus} -- the tendency of randomized transformations to yield aligned…

The existing work shows that the neural network trained by naive gradient-based optimization method is prone to adversarial attacks, adds small malicious on the ordinary input is enough to make the neural network wrong. At the same time,…

Evaluating adversarial robustness amounts to finding the minimum perturbation needed to have an input sample misclassified. The inherent complexity of the underlying optimization requires current gradient-based attacks to be carefully…

Prompt-based learning is a new language model training paradigm that adapts the Pre-trained Language Models (PLMs) to downstream tasks, which revitalizes the performance benchmarks across various natural language processing (NLP) tasks.…

Deep learning on graph structures has shown exciting results in various applications. However, few attentions have been paid to the robustness of such models, in contrast to numerous research work for image or text adversarial attack and…

Reliable evaluation of adversarial defenses is a challenging task, currently limited to an expert who manually crafts attacks that exploit the defense's inner workings or approaches based on an ensemble of fixed attacks, none of which may…

Black-box adversarial attacks present a realistic threat to action recognition systems. Existing black-box attacks follow either a query-based approach where an attack is optimized by querying the target model, or a transfer-based approach…

Recent studies on adversarial examples expose vulnerabilities of natural language processing (NLP) models. Existing techniques for generating adversarial examples are typically driven by deterministic hierarchical rules that are agnostic to…

Deep neural networks (DNNs) have transformed several artificial intelligence research areas including computer vision, speech recognition, and natural language processing. However, recent studies demonstrated that DNNs are vulnerable to…

We address the problem of allocating limited resources in a network under persistent yet statistically unknown adversarial attacks. Each node in the network may be degraded, but not fully disabled, depending on its available defensive…

This work tackles a critical challenge in AI safety research under limited compute: given a fixed computation budget, how can one maximize the strength of iterative adversarial attacks? Coarsely reducing the number of attack iterations…

Cybersecurity risk analysis plays an essential role in supporting organizations make effective decision about how to manage and control cybersecurity risk. Cybersecurity risk is a function of the interplay between the defender, i.e., the…

Recently, adversarial attack methods have been developed to challenge the robustness of machine learning models. However, mainstream evaluation criteria experience limitations, even yielding discrepancies among results under different…

Attack detection is usually approached as a classification problem. However, standard classification tools often perform poorly because an adaptive attacker can shape his attacks in response to the algorithm. This has led to the recent…

Since Biggio et al. (2013) and Szegedy et al. (2013) first drew attention to adversarial examples, there has been a flood of research into defending and attacking machine learning models. However, almost all proposed attacks assume…

Clustering algorithms are used in a large number of applications and play an important role in modern machine learning-- yet, adversarial attacks on clustering algorithms seem to be broadly overlooked unlike supervised learning. In this…