Files
myWiki/concepts/adversarial-robustness.md

35 lines
1.2 KiB
Markdown
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

---
title: "对抗鲁棒性 (Adversarial Robustness)"
created: 2026-07-04
updated: 2026-07-04
type: concept
tags: [robustness, adversarial, security, perturbation]
sources: []
---
# 对抗鲁棒性 (Adversarial Robustness)
模型在故意设计的微小输入扰动(对抗攻击)下保持正确预测的能力。
## 与鲁棒性认证的关系
- **对抗训练**:在训练中加入对抗样本提升鲁棒性(经验性)
- **鲁棒性认证**[[robustness-certification]]):给出严格的数学保证——在特定扰动范围内预测必定不变
- 认证是更强的声明,但通常更保守
## 常见攻击与防御
- 攻击FGSM, PGD, C&W, AutoAttack
- 防御:对抗训练, 随机平滑([[randomized-smoothing]], 输入去噪
## 与语义鲁棒性的区别
对抗鲁棒性关注**恶意设计的**、像素级的不可察觉扰动;语义鲁棒性关注**自然发生的**语义属性变化(形状、风格、背景等)。[[semantic-robustness-certification|语义鲁棒性认证]] 将问题推进到语义层。
## 参考
- [[robustness-certification|鲁棒性认证]]
- [[randomized-smoothing|随机平滑]]
- [[semantic-robustness-certification|语义鲁棒性认证]]
- [[distribution-shift|分布偏移]]