Awesome-ML-Supply-Chain-Security-Papers

A curated list of Meachine learning Security & Privacy papers, inspired by awesome-php and awesome-computer-vision.

Contributing

Please feel free to pull requests to add papers.

Markdown format：

- **Paper Name.**
  [[pdf](link)]
  [[code](link)]
  `keywords: keyword 1, keyword 2, keyword 3.`
  - author 1, author 2, and author 3. *conference name (abbr), year. (CCF Rank)*

Table of Contents

• 1. Backdoor Attack & Defense
  • 1.1. Image Segmentation (图像分割)
  • 1.2. Image Classification (图像分类)
  • 1.3. Diffusion Model (扩散模型)
  • 1.4. Reinforcement Learning (强化学习)
  • 1.5. Recommendation Systems (推荐系统)
  • 1.6. Few-shot Learning (小样本学习)
  • 1.7. Federated Learning (联邦学习)
  • 1.X. Others
• 2. Adversarial Attack & Defense

List of Papers

1. Backdoor Attack & Defense

1.1. Image Segmentation

• BadSAM: Exploring Security Vulnerabilities of SAM via Backdoor Attacks (Student Abstract).
  • Zihan Guan, Mengxuan Hu, Zhongliang Zhou, Jielu Zhang, Sheng Li, Ninghao Liu. AAAI, 2024.

1.2. Image Classification

1.2.1. 3D Point Cloud Classification

• Invisible Backdoor Attack against 3D Point Cloud Classifier in Graph Spectral Domain.
  • Linkun Fan, Fazhi He, Tongzhen Si, Wei Tang, Bing Li. AAAI, 2024.

1.3. Diffusion Model

• Personalization as a Shortcut for Few-Shot Backdoor Attack against Text-to-Image Diffusion Models.
  • Yihao Huang, Felix Juefei-Xu, Qing Guo, Jie Zhang, Yutong Wu, Ming Hu, Tianlin Li, Geguang Pu, Yang Liu. AAAI, 2024.
• Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift.
  • Shengwei An, Sheng-Yen Chou, Kaiyuan Zhang, Qiuling Xu, Guanhong Tao, Guangyu Shen, Siyuan Cheng, Shiqing Ma, Pin-Yu Chen, Tsung-Yi Ho, Xiangyu Zhang. AAAI, 2024.

1.4. Reinforcement Learning

• BadRL: Sparse Targeted Backdoor Attack against Reinforcement Learning.
  • Jing Cui, Yufei Han, Yuzhe Ma, Jianbin Jiao, Junge Zhang. AAAI, 2024.

1.5. Recommendation Systems

• Backdoor Adjustment via Group Adaptation for Debiased Coupon Recommendations.
  • Junpeng Fang, Gongduo Zhang, Qing Cui, Caizhi Tang, Lihong Gu, Longfei Li, Jinjie Gu, Jun Zhou. AAAI, 2024.

1.6. Few-shot Learning

• Does Few-Shot Learning Suffer from Backdoor Attacks?
  • AAAI, 2024.

1.7. Federated Learning

• Beyond Traditional Threats: A Persistent Backdoor Attack on Federated Learning.

  • AAAI, 2024.

• Resisting Backdoor Attacks in Federated Learning via Bidirectional Elections and Individual Perspective.

  • AAAI, 2024.

• Chronic Poisoning: Backdoor Attack against Split Learning.

  • AAAI, 2024.

• On the Vulnerability of Backdoor Defenses for Federated Learning.

  • AAAI, 2023.

• Poisoning with Cerberus: Stealthy and Colluded Backdoor Attack against Federated Learning.

  • AAAI, 2023.

• A Spatiotemporal Backdoor Attack Against Behavior-Oriented Decision Makers in Metaverse: From Perspective of Autonomous Driving. [pdf] keywords: Spatiotemporal Backdoor Attack, Reinforcement Learning.

  • Yinbo Yu, Jiajia Liu, Hongzhi Guo, Bomin Mao, Nei Kato. IEEE Journal of Selected Areas in Communications (JSAC), 2024. (CCF-A)

• WaTrojan: Wavelet domain trigger injection for backdoor attacks. [pdf]

1.X. Defense

• Inspecting Prediction Confidence for Detecting Black-Box Backdoor Attacks.
  • AAAI, 2024.
• UMA: Facilitating Backdoor Scanning via Unlearning-Based Model Ablation.
  • AAAI, 2024.
• DataElixir: Purifying Poisoned Dataset to Mitigate Backdoor Attacks via Diffusion Models.
  • AAAI, 2024.
• SEER: Backdoor Detection for Vision-Language Models through Searching Target Text and Image Trigger Jointly
  • AAAI, 2024.
• Defending Backdoor Attacks on Vision Transformer via Patch Processing.
  • AAAI, 2023.

1.XX. Others

• Progressive Poisoned Data Isolation for Training-Time Backdoor Defense.
  • Yiming Chen, Haiwei Wu, Jiantao Zhou. AAAI, 2024.
• Conditional Backdoor Attack via JPEG Compression.
  • Qiuyu Duan, Zhongyun Hua, Qing Liao, Yushu Zhang, Leo Yu Zhang. AAAI, 2024.
• A Dual Stealthy Backdoor: From Both Spatial and Frequency Perspectives.
  • AAAI, 2024.
• COMBAT: Alternated Training for Effective Clean-Label Backdoor Attacks.
  • AAAI, 2024.
• Temporal-Distributed Backdoor Attack against Video Based Action Recognition.
  • AAAI, 2024.
• Backdoor Attacks via Machine Unlearning.
  • AAAI, 2024.
• Poisoning-Based Backdoor Attacks in Computer Vision.
  • AAAI, 2023.

2. Adversarial Attack & Defense