Stability and Generalization in Free Adversarial Training

원문 초록

While adversarial training methods have significantly improved the robustness of deep neural networks against norm-bounded adversarial perturbations, the generalization gap between their performance on training and test data is considerably greater than that of standard empirical risk minimization. Recent studies have aimed to connect the generalization properties of adversarially trained classifiers to the min-max optimization algorithm used in their training. In this work, we analyze the interconnections between generalization and optimization in adversarial training using the algorithmic stability framework. Specifically, our goal is to compare the generalization gap of neural networks trained using the vanilla adversarial training method, which fully optimizes perturbations at every iteration, with the free adversarial training method, which simultaneously optimizes norm-bounded perturbations and classifier parameters. We prove bounds on the generalization error of these methods, indicating that the free adversarial training method may exhibit a lower generalization gap between training and test samples due to its simultaneous min-max optimization of classifier weights and perturbation variables. We conduct several numerical experiments to evaluate the train-to-test generalization gap in vanilla and free adversarial training methods. Our empirical findings also suggest that the free adversarial training method could lead to a smaller generalization gap over a similar number of training iterations. The paper code is available at https://github.com/Xiwei-Cheng/Stability_FreeAT.