Saved in:
Bibliographic Details
Main Authors: Yu-Hang, Wang, ying, Liu, liang, Fang, Xuelin, Wang, Guo, Junkang, Li, Shiwei, Gao, Lei, Liu, Jian, Yin, Wenfei
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.15685
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Adversarial Training (AT) is a cornerstone defense, but many variants overlook foundational feature representations by primarily focusing on stronger attack generation. We introduce Adversarial Evolution Training (AET), a simple yet powerful framework that strategically prepends an Empirical Risk Minimization (ERM) phase to conventional AT. We hypothesize this initial ERM phase cultivates a favorable feature manifold, enabling more efficient and effective robustness acquisition. Empirically, AET achieves comparable or superior robustness more rapidly, improves clean accuracy, and cuts training costs by 8-25\%. Its effectiveness is shown across multiple datasets, architectures, and when augmenting established AT methods. Our findings underscore the impact of feature pre-conditioning via standard training for developing more efficient, principled robust defenses. Code is available in the supplementary material.