后门攻击 & 对抗攻击 resources

后门攻击

知乎问答 & 公众号：

1. 后门学习(Backdoor Learning)介绍及资源汇总
2. 浅谈深度学习后门攻击
3. Backdoor Learning: A SurveyAI中的后门攻击及防御-实战篇
4. 如何攻击深度学习系统——后门攻防
5. 毒墨水：一种隐蔽且鲁棒的后门攻击
6. 深度学习中的后门攻击综述【 信 息 安 全 学 报】
7. 对深度学习模型的后门攻击在现实世界中是否可行？
8. 如何保护深度学习系统-后门防御
9. 复旦大学｜基于文本风格的隐式NLP后门攻击（USENIX-SEC 2022）
10. 联邦学习中的后门攻击
11. 医疗图像后门攻击的解释
12. 每周论文讨论(8) | 图神经网络后门攻击
13. BadNets-深度学习后门攻击的开篇之作
14. 【直播】【AI TIME】回顾与展望神经网络的后门攻击与防御

paper

1. Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
2. Dynamic Backdoor Attacks Against Machine Learning Models
3. Backdoor Attacks Against Deep Learning Systems in the Physical World
4. Backdoor Learning: A Survey

GitHub paper resource:

1. backdoor learning resource
2. OpenBackdoor

对抗攻击

1. 综述论文：对抗攻击的12种攻击方法和15种防御方法
2. 一文尽览！文本对抗攻击基础、前沿及相关资源
3. CV||对抗攻击领域综述（adversarial attack）
4. 针对深度学习的对抗攻击综述
5. 人工智能对抗攻击研究综述
6. 文本对抗攻击之综述
7. 对抗样本（一）以综述入门
8. OpenAttack：文本对抗攻击工具包
9. 什么是nlp中的对抗示例
10. 面向自然语言处理的对抗攻防与鲁棒性分析综述
11. 基于梯度的NLP对抗攻击方法

paper：

1. Adversarial Attack and Defense: A Survey
2. Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey
3. A survey on adversarial attacks and defences
4. A Survey on Universal Adversarial Attack
5. Adversarial Attacks and Defences: A Survey
6. Adversarial Attack and Defense on Graph Data: A Survey
7. Towards More Practical Adversarial Attacks on Graph Neural Networks
8. GNNGUARD: Defending Graph Neural Networks against Adversarial Attacks
9. Adversarial Attacks on Graph Neural Networks via Meta Learning
10. Adversarial Attacks on Deep-learning Models in Natural Language Processing: A Survey
11. A survey of Adversarial Defences and Robustness in NLP
12. Adversarial Attacks on Deep Learning Models in Natural Language Processing: A Survey

github：

1. Must-read Papers on Textual Adversarial Attack and Defense (TAAD)

2. Adversarial-Attack-Papers

3. The Papers of Adversarial Examples

tools:

1. https://pytorch.org/tutorials/beginner/fgsm_tutorial.html
2. Adversarial-Attacks-PyTorch
3. Open attack