On robust overfitting: adversarial training induced distribution matters
Adversarial training may be regarded as standard training with a modified loss function. But its generalization error appears much larger than standard training under standard loss. This phenomenon, known as robust overfitting, has attracted significant research attention and remains largely as a mystery. In this paper, we first show empirically that robust overfitting correlates with the increasing generalization difficulty of the perturbation-induced distributions along the trajectory of adversarial training (specifically PGD-based adversarial training). We then provide a novel upper bound for generalization error with respect to the perturbation-induced distributions, in which a notion of the perturbation operator, referred to "local dispersion", plays an important role. Experimental results are presented to validate the usefulness of the bound and various additional insights are provided.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Boundary Adversarial Examples Against Adversarial Overfitting
Standard adversarial training approaches suffer from robust overfitting where the robust accuracy decreases when models are adversarially trained for too long. The origin of this problem is still unclear and conflicting …
MemorizationData Quality Matters For Adversarial Training: An Empirical Study
Multiple intriguing problems are hovering in adversarial training, including robust overfitting, robustness overestimation, and robustness-accuracy trade-off. These problems pose great challenges to both reliable evaluat…
Adversarial RobustnessDistributionally and Adversarially Robust Logistic Regression via Intersecting Wasserstein Balls
Adversarially robust optimization (ARO) has emerged as the *de facto* standard for training models that hedge against adversarial attacks in the test stage. While these models are robust against adversarial attacks, they…
regressionUnderstanding Robust Overfitting of Adversarial Training and Beyond
Robust overfitting widely exists in adversarial training of deep networks. The exact underlying reasons for this are still not completely understood. Here, we explore the causes of robust overfitting by comparing the dat…
Adversarial RobustnessData AblationTowards Rapid and Robust Adversarial Training with One-Step Attacks
Adversarial training is the most successful empirical method for increasing the robustness of neural networks against adversarial attacks. However, the most effective approaches, like training with Projected Gradient Des…