Position: Towards Resilience Against Adversarial Examples
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.
Code (0)
등록된 구현이 없습니다.
Tasks
PositionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Delving into adversarial attacks on deep policies
Adversarial examples have been shown to exist for a variety of deep learning architectures. Deep reinforcement learning has shown promising results on training agent policies directly on raw inputs such as image pixels. …
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)$n$-ML: Mitigating Adversarial Examples via Ensembles of Topologically Manipulated Classifiers
This paper proposes a new defense called $n$-ML against adversarial examples, i.e., inputs crafted by perturbing benign inputs by small amounts to induce misclassifications by classifiers. Inspired by $n$-version program…
General ClassificationAdversarial-Ensemble Kolmogorov Arnold Networks for Enhancing Indoor Wi-Fi Positioning: A Defensive Approach Against Spoofing and Signal Manipulation Attacks
The research presents a study on enhancing the robustness of Wi-Fi-based indoor positioning systems against adversarial attacks. The goal is to improve the positioning accuracy and resilience of these systems under two a…
Kolmogorov-Arnold NetworksUnderstanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks
Recent works have shown that deep neural networks are vulnerable to adversarial examples that find samples close to the original image but can make the model misclassify. Even with access only to the model's output, an a…
Image ClassificationA Robust Defense against Adversarial Attacks on Deep Learning-based Malware Detectors via (De)Randomized Smoothing
Deep learning-based malware detectors have been shown to be susceptible to adversarial malware examples, i.e. malware examples that have been deliberately manipulated in order to avoid detection. In light of the vulnerab…
Adversarial Robustness