The resources related to the trustworthiness of large models (LMs) across multiple dimensions (e.g., safety, security, and privacy), with a special focus on multi-modal LMs (e.g., vision-language models and diffusion models).

• This repo is in progress 🌱 (currently manually collected).

• Badges:

  • Model:

    • 
    • 
    • 
    • 

  • Comment: ...

  • Venue: ...

• 🌻 Welcome to recommend resources to us via Issues with the following format (please fill in this table):

• [2024.05.13] We collected 7 related papers from S&P'24!
• [2024.04.27] We adjusted the categories.
• [2024.01.20] We collected 3 related papers from NDSS'24!
• [2024.01.17] We collected 108 related papers from ICLR'24!
• [2024.01.09] 🚀 LM-SSP is released!

• Book (1)
• Competition (5)
• Leaderboard (3)
• Toolkit (7)
• Survey (23)
• Paper (744)
  • A. Safety (453)
    • A0. General (6)
    • A1. Jailbreak (138)
    • A2. Alignment (49)
    • A3. Deepfake (39)
    • A4. Ethics (5)
    • A5. Fairness (50)
    • A6. Hallucination (101)
    • A7. Prompt Injection (13)
    • A8. Toxicity (52)
  • B. Security (118)
    • B0. General (1)
    • B1. Adversarial Examples (63)
    • B2. Poison & Backdoor (47)
    • B3. System (7)
  • C. Privacy (173)
    • C0. General (15)
    • C1. Contamination (8)
    • C2. Copyright (59)
    • C3. Data Reconstruction (21)
    • C4. Membership Inference Attacks (9)
    • C5. Model Extraction (7)
    • C6. Privacy-Preserving Computation (23)
    • C7. Property Inference Attacks (1)
    • C8. Unlearning (30)

• Organizers: Tianshuo Cong (丛天硕), Xinlei He (何新磊), Zhengyu Zhao (赵正宇), Yugeng Liu (刘禹更), Delong Ran (冉德龙)

• This project is inspired by LLM Security, Awesome LLM Security, LLM Security & Privacy, UR2-LLMs, PLMpapers, EvaluationPapers4ChatGPT