先用标准训练预热模型特征，再做对抗训练，提速且更鲁棒。
Ignition Phase : Standard Training for Fast Adversarial Robustness
- 先做标准训练（ERM）再做对抗训练，提升特征质量
- 相比传统方法，训练速度提升8%-25%，鲁棒性相当或更好
- 适合追求高效防御的模型开发者，尤其适用于多种架构
对抗训练（AT）是主流防御方法，但多数变体过于关注攻击强度，忽视基础特征表示。本文提出对抗演化训练（AET），在传统AT前增加一个经验风险最小化（ERM）阶段。我们假设该初始阶段能构建有利的特征流形，从而更高效地获得鲁棒性。实验表明，AET在多个数据集、模型架构上均实现相当或更优的鲁棒性，同时提升干净准确率，并将训练成本降低8%至25%。该方法可无缝集成到现有AT框架中。结果表明，通过标准训练预处理特征，可显著提升鲁棒防御的效率与合理性。代码已在附录中提供。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。