On Achieving Optimal Adversarial Test Error
We first elucidate various fundamental properties of optimal adversarial predictors: the structure of optimal adversarial convex predictors in terms of optimal adversarial zero-one predictors, bounds relating the adversarial convex loss to the adversarial zero-one loss, and the fact that continuous predictors can get arbitrarily close to the optimal adversarial error for both convex and zero-one losses. Applying these results along with new Rademacher complexity bounds for adversarial training near initialization, we prove that for general data distributions and perturbation sets, adversarial training on shallow networks with early stopping and an idealized optimal adversary is able to achieve optimal adversarial test error. By contrast, prior theoretical work either considered specialized data distributions or only provided training error guarantees.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Interpolated Adversarial Training: Achieving Robust Neural Networks without Sacrificing Too Much Accuracy
Adversarial robustness has become a central goal in deep learning, both in the theory and the practice. However, successful methods to improve the adversarial robustness (such as adversarial training) greatly hurt genera…
Adversarial RobustnessTowards Optimal Adversarial Robust Reinforcement Learning with Infinity Measurement Error
Ensuring the robustness of deep reinforcement learning (DRL) agents against adversarial attacks is critical for their trustworthy deployment. Recent research highlights the challenges of achieving state-adversarial robus…
Adversarial RobustnessDeep Reinforcement Learningreinforcement-learningReinforcement LearningClassifier-independent Lower-Bounds for Adversarial Robustness
We theoretically analyse the limits of robustness to test-time adversarial and noisy examples in classification. Our work focuses on deriving bounds which uniformly apply to all classifiers (i.e all measurable functions …
Adversarial AttackAdversarial RobustnessGeneral ClassificationBypassing the Simulator: Near-Optimal Adversarial Linear Contextual Bandits
We consider the adversarial linear contextual bandit problem, where the loss vectors are selected fully adversarially and the per-round action set (i.e. the context) is drawn from a fixed distribution. Existing methods f…
Computational EfficiencyMulti-Armed BanditsAdversarial Question Answering Robustness: A Multi-Level Error Analysis and Mitigation Study
Question answering (QA) systems achieve impressive performance on standard benchmarks like SQuAD, but remain vulnerable to adversarial examples. This project investigates the adversarial robustness of transformer models …
Adversarial RobustnessContrastive LearningQuestion AnsweringData Augmentation