Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2506.15685 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915545267306496 |
|---|---|
| author | Yu-Hang, Wang ying, Liu liang, Fang Xuelin, Wang Guo, Junkang Li, Shiwei Gao, Lei Liu, Jian Yin, Wenfei |
| author_facet | Yu-Hang, Wang ying, Liu liang, Fang Xuelin, Wang Guo, Junkang Li, Shiwei Gao, Lei Liu, Jian Yin, Wenfei |
| 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_15685 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Ignition Phase : Standard Training for Fast Adversarial Robustness Yu-Hang, Wang ying, Liu liang, Fang Xuelin, Wang Guo, Junkang Li, Shiwei Gao, Lei Liu, Jian Yin, Wenfei Machine Learning Artificial Intelligence 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. |
| title | Ignition Phase : Standard Training for Fast Adversarial Robustness |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2506.15685 |