Towards Achieving Adversarial Robustness Beyond Perceptual Limits
The vulnerability of Deep Neural Networks to Adversarial Attacks has fuelled research towards building robust models. While most Adversarial Training algorithms aim towards defending attacks constrained within low magnitude $\ell_p$ norm bounds, real-world adversaries are not limited by such constraints. In this work, we aim to achieve adversarial robustness within larger bounds, against perturbations that may be perceptible, but do not change human (or Oracle) prediction. The presence of images that flip Oracle predictions and those that do not, makes this a challenging setting for adversarial robustness. We discuss the ideal goals of an adversarial defense algorithm beyond perceptual limits, and further highlight the shortcomings of naively extending existing training algorithms to higher perturbation bounds. In order to overcome these shortcomings, we propose a novel defense, Oracle-Aligned Adversarial Training (OA-AT), to align the predictions of the network with that of an Oracle during adversarial training. The proposed approach achieves state-of-the-art performance at large epsilon bounds (such as an $\ell_\infty$ bound of $16/255$ on CIFAR-10) while outperforming existing defenses (AWP, TRADES and PGD-AT) at standard perturbation bounds ($8/255$) as well.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial DefenseAdversarial RobustnessMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Scaling Adversarial Training to Large Perturbation Bounds
The vulnerability of Deep Neural Networks to Adversarial Attacks has fuelled research towards building robust models. While most Adversarial Training algorithms aim at defending attacks constrained within low magnitude L…
Adversarial DefenseAdversarial RobustnessGeoThreat: Transferable Targeted Adversarial Attacks on Large Vision-Language Models for Remote Sensing Image Interpretation
Adversarial attacks against large vision-language models (LVLMs) serve as an effective means of assessing their robustness in cross-modal semantic understanding. Existing studies mainly focus on corrupting visual inputs …
Adversarial AttackHarnessing Perceptual Adversarial Patches for Crowd Counting
Crowd counting, which has been widely adopted for estimating the number of people in safety-critical scenes, is shown to be vulnerable to adversarial examples in the physical world (e.g., adversarial patches). Though har…
Crowd CountingPerceptual Adversarial Robustness: Defense Against Unseen Threat Models
A key challenge in adversarial robustness is the lack of a precise mathematical characterization of human perception, used in the very definition of adversarial attacks that are imperceptible to human eyes. Most current …
Adversarial DefenseAdversarial RobustnessPerceptual DistanceAdversarially Robust 3D Point Cloud Recognition Using Self-Supervisions
3D point cloud data is increasingly used in safety-critical applications such as autonomous driving. Thus, the robustness of 3D deep learning models against adversarial attacks becomes a major consideration. In this pape…
Adversarial RobustnessAutonomous DrivingSelf-Supervised Learning