数据稀缺下的鲁棒性：面向演化威胁的少样本持续对抗训练
Robustness Under Data Scarcity: Few-Shot Continual Adversarial Training for Evolving Threats
把少样本持续对抗训练这一设定引入视觉模型鲁棒性维护，其高斯混合原型回放与对抗间隔损失可直接用于在数据受限、攻击分布不断漂移的场景下持续更新分类器而不遗忘旧攻击域。
原文依据 Few-shot Continual Adversarial Training, where only a small number of adversarial examples are available per stage
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论深度学习模型仍然极易受到不断演化的对抗攻击的影响。现有持续对抗训练方法通常假设每个阶段都有充足的对抗数据，而现实场景中数据往往十分有限。本文研究少样本持续对抗训练这一设定，即每个阶段仅有少量对抗样本可用，该设定在实现鲁棒泛化与缓解灾难性遗忘方面带来重大挑战。为应对这些挑战，我们提出一种新的持续对抗训练框架，包含三个关键组件：(i) 对抗间隔损失，显式地将干净样本推离决策边界，以增强特征判别性；(ii) 高斯混合模型原型回放策略，合成具有代表性的伪特征，以保留对过去对抗域的知识；(iii) 多域平衡损失，引导参数更新，从而在多种攻击分布上稳定学习。在 ImageNet-1K 与 CIFAR-100 上的大量实验表明，我们的方法在多种对抗设定下的干净精度与鲁棒精度上均持续优于最优方法。代码将公开。
英文原文摘要 1279 字符
Deep learning models remain highly vulnerable to evolving adversarial attacks. While existing continual adversarial training approaches often assume abundant adversarial data at each stage, real-world scenarios frequently involve limited data availability. This paper addresses the setting of Few-shot Continual Adversarial Training, where only a small number of adversarial examples are available per stage, presenting major challenges in achieving robust generalization and mitigating catastrophic forgetting. To tackle these challenges, we propose a novel continual adversarial training framework that incorporates three key components: (i) an Adversarial Margin loss that explicitly pushes clean samples away from decision boundaries to enhance feature discrimination; (ii) a Gaussian mixture model Prototype Replay strategy that synthesizes representative pseudo-features to preserve knowledge of past adversarial domains; and (iii) a Multi-Domain Balanced loss that guides updates to stabilize learning across diverse attack distributions. Extensive experiments on ImageNet-1K and CIFAR-100 demonstrate that our approach consistently outperforms state-of-the-art methods in both clean and robust accuracy across a variety of adversarial settings. The code will be released.