20260706:新增一些文章
This commit is contained in:
34
concepts/adversarial-robustness.md
Normal file
34
concepts/adversarial-robustness.md
Normal file
@@ -0,0 +1,34 @@
|
||||
---
|
||||
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]]
|
||||
Reference in New Issue
Block a user