Papers › Stability Analysis and Generalization Bounds of Adversarial Training
Stability Analysis and Generalization Bounds of Adversarial Training
Jiancong Xiao, Yanbo Fan, Ruoyu Sun, Jue Wang, Zhi-Quan Luo
In adversarial machine learning, deep neural networks can fit the adversarial examples on the training dataset but have poor generalization ability on the test set. This phenomenon is called robust overfitting, and it can be observed when adversarially training neural nets on common datasets, including SVHN, CIFAR-10, CIFAR-100, and ImageNet. In this paper, we study the robust overfitting issue of adversarial training by using tools from uniform stability. One major challenge is that the outer function (as a maximization of the inner function) is nonsmooth, so the standard technique (e.g., hardt et al., 2016) cannot be applied. Our approach is to consider η-approximate smoothness: we show that the outer function satisfies this modified smoothness assumption with η being a constant related to the adversarial perturbation ϵ. Based on this, we derive stability-based generalization bounds for stochastic gradient descent (SGD) on the general class of η-approximate smooth functions, which covers the adversarial loss. Our results suggest that robust test accuracy decreases in ϵ when T is large, with a speed between Ω(ϵ√(T)) and 𝒪(ϵT). This phenomenon is also observed in practice. Additionally, we show that a few popular techniques for adversarial training (e.g., early stopping, cyclic learning rate, and stochastic weight averaging) are stability-promoting in theory.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections