Position: Towards Resilience Against Adversarial Examples

• URL: http://arxiv.org/abs/2405.01349v2
• Date: Tue, 08 Oct 2024 15:56:45 GMT
• Title: Position: Towards Resilience Against Adversarial Examples
• Authors: Sihui Dai, Chong Xiang, Tong Wu, Prateek Mittal,
• Abstract summary: We provide a definition of adversarial resilience and outline considerations of designing an adversarially resilient defense. We then introduce a subproblem of adversarial resilience which we call continual adaptive robustness. We demonstrate the connection between continual adaptive robustness and previously studied problems of multiattack robustness and unforeseen attack robustness.
• Score: 42.09231029292568
• License:
• Abstract: Current research on defending against adversarial examples focuses primarily on achieving robustness against a single attack type such as $\ell_2$ or $\ell_{\infty}$-bounded attacks. However, the space of possible perturbations is much larger than considered by many existing defenses and is difficult to mathematically model, so the attacker can easily bypass the defense by using a type of attack that is not covered by the defense. In this position paper, we argue that in addition to robustness, we should also aim to develop defense algorithms that are adversarially resilient -- defense algorithms should specify a means to quickly adapt the defended model to be robust against new attacks. We provide a definition of adversarial resilience and outline considerations of designing an adversarially resilient defense. We then introduce a subproblem of adversarial resilience which we call continual adaptive robustness, in which the defender gains knowledge of the formulation of possible perturbation spaces over time and can then update their model based on this information. Additionally, we demonstrate the connection between continual adaptive robustness and previously studied problems of multiattack robustness and unforeseen attack robustness and outline open directions within these fields which can contribute to improving continual adaptive robustness and adversarial resilience.

Related papers

• Adversarial Markov Games: On Adaptive Decision-Based Attacks and Defenses [21.759075171536388]
  We show how attacks but also defenses can benefit by it and by learning from each other through interaction. We demonstrate that active defenses, which control how the system responds, are a necessary complement to model hardening when facing decision-based attacks. We lay out effective strategies in ensuring the robustness of ML-based systems deployed in the real-world.
  arXiv  Detail & Related papers  (2023-12-20T21:24:52Z)
• Mutual-modality Adversarial Attack with Semantic Perturbation [81.66172089175346]
  We propose a novel approach that generates adversarial attacks in a mutual-modality optimization scheme. Our approach outperforms state-of-the-art attack methods and can be readily deployed as a plug-and-play solution.
  arXiv  Detail & Related papers  (2023-12-20T05:06:01Z)
• Continual Adversarial Defense [37.37029638528458]
  A defense system continuously collects adversarial data online to quickly improve itself. Continual adaptation to new attacks without catastrophic forgetting, few-shot adaptation, memory-efficient adaptation, and high accuracy on both clean and adversarial data. In particular, CAD is capable of quickly adapting with minimal budget and a low cost of defense failure while maintaining good performance against previous attacks.
  arXiv  Detail & Related papers  (2023-12-15T01:38:26Z)
• Randomness in ML Defenses Helps Persistent Attackers and Hinders Evaluators [49.52538232104449]
  It is becoming increasingly imperative to design robust ML defenses. Recent work has found that many defenses that initially resist state-of-the-art attacks can be broken by an adaptive adversary. We take steps to simplify the design of defenses and argue that white-box defenses should eschew randomness when possible.
  arXiv  Detail & Related papers  (2023-02-27T01:33:31Z)
• Can Adversarial Training Be Manipulated By Non-Robust Features? [64.73107315313251]
  Adversarial training, originally designed to resist test-time adversarial examples, has shown to be promising in mitigating training-time availability attacks. We identify a novel threat model named stability attacks, which aims to hinder robust availability by slightly perturbing the training data. Under this threat, we find that adversarial training using a conventional defense budget $epsilon$ provably fails to provide test robustness in a simple statistical setting.
  arXiv  Detail & Related papers  (2022-01-31T16:25:25Z)
• Adaptive Feature Alignment for Adversarial Training [56.17654691470554]
  CNNs are typically vulnerable to adversarial attacks, which pose a threat to security-sensitive applications. We propose the adaptive feature alignment (AFA) to generate features of arbitrary attacking strengths. Our method is trained to automatically align features of arbitrary attacking strength.
  arXiv  Detail & Related papers  (2021-05-31T17:01:05Z)
• Automated Discovery of Adaptive Attacks on Adversarial Defenses [14.633898825111826]
  We present a framework that automatically discovers an effective attack on a given model with an unknown defense. We show it outperforms AutoAttack, the current state-of-the-art tool for reliable evaluation of adversarial defenses.
  arXiv  Detail & Related papers  (2021-02-23T18:43:24Z)
• Guided Adversarial Attack for Evaluating and Enhancing Adversarial Defenses [59.58128343334556]
  We introduce a relaxation term to the standard loss, that finds more suitable gradient-directions, increases attack efficacy and leads to more efficient adversarial training. We propose Guided Adversarial Margin Attack (GAMA), which utilizes function mapping of the clean image to guide the generation of adversaries. We also propose Guided Adversarial Training (GAT), which achieves state-of-the-art performance amongst single-step defenses.
  arXiv  Detail & Related papers  (2020-11-30T16:39:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.