Position: Towards Resilience Against Adversarial Examples
Not on the map. Why?
Abstract (arXiv)
Current research on defending against adversarial examples focuses primarily on achieving robustness against a single attack type such as ℓ2 or ℓ∞-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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 55 of its 88 references that are in the map. First posted on arXiv 2 May 2024.
Builds on
55 of 88 references.
References · 55
- 2020Denoising Diffusion Probabilistic Modelscited by 20,851
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2013Intriguing properties of neural networkscited by 5,114
- 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
- 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
- 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,565
- 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
- 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
38 more
- 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
- 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
- 2018Robustness May Be at Odds with Accuracycited by 873
- 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
- 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
- 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
- 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
- 2017Adversarial Patchcited by 514
- 2019Unlabeled Data Improves Adversarial Robustnesscited by 415
- 2021Improving Robustness using Generated Datacited by 233
- 2018Spatially Transformed Adversarial Examplescited by 195
- 2019Adversarial Training and Robustness for Multiple Perturbationscited by 182
- 2018Disentangling Adversarial Robustness and Generalizationcited by 171
- 2022NOTE: Robust Continual Test-time Adaptation Against Temporal Correlationcited by 150
- 2020Randomized Smoothing of All Shapes and Sizescited by 146
- 2020Perceptual Adversarial Robustness: Defense Against Unseen Threat Modelscited by 137
- 2021Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?cited by 113
- 2020Certified Defenses for Adversarial Patchescited by 100
- 2019Wasserstein Adversarial Examples via Projected Sinkhorn Iterationscited by 89
- 2019Adversarial Robustness Against the Union of Multiple Perturbation Modelscited by 88
- 2019Functional Adversarial Attackscited by 82
- 2021PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifiercited by 63
- 2024EasyJailbreak: A Unified Framework for Jailbreaking Large Language Modelscited by 57
- 2020Learning perturbation sets for robust machine learningcited by 48
- 2019An Alternative Surrogate Loss for PGD-based Adversarial Testingcited by 45
- 2020Black-Box Certification with Randomized Smoothing: A Functional Optimization Based Frameworkcited by 45
- 2020Dual Manifold Adversarial Robustness: Defense against Lp and non-Lp Adversarial Attackscited by 45
- 2019Provable robustness against all adversarial lp-perturbations for p≥ 1cited by 39
- 2020Randomization matters. How to defend against strong adversarial attackscited by 37
- 2022The Many Faces of Adversarial Riskcited by 28
- 2023R-LPIPS: An Adversarially Robust Perceptual Similarity Metriccited by 27
- 2022Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbationscited by 26
- 2020Stronger and Faster Wasserstein Adversarial Attackscited by 25
- 2021Adversarially Robust Learning with Unknown Perturbation Setscited by 24
- 2021Adversarial Robustness against Multiple and Single lp-Threat Models via Quick Fine-Tuning of Robust Classifierscited by 23
- 2021Mixed Nash Equilibria in the Adversarial Examples Gamecited by 22
- 2023Distracting Downpour: Adversarial Weather Attacks for Motion Estimationcited by 15
- 2022Provable Defense Against Geometric Transformationscited by 14
50 most cited of 55 All 55 (JSON)
Built on by
Citing papers per year: 2026: 1.
1 paper.