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):

• [2024.08.17] We collected 34 related papers from ACL'24!
• [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 (2)
• Competition (5)
• Leaderboard (3)
• Toolkit (9)
• Survey (32)
• Paper (1215)
  • A. Safety (678)
    • A0. General (15)
    • A1. Jailbreak (263)
    • A2. Alignment (73)
    • A3. Deepfake (55)
    • A4. Ethics (5)
    • A5. Fairness (54)
    • A6. Hallucination (108)
    • A7. Prompt Injection (39)
    • A8. Toxicity (66)
  • B. Security (184)
    • B0. General (7)
    • B1. Adversarial Examples (80)
    • B2. Poison & Backdoor (86)
    • B3. System (11)
  • C. Privacy (353)
    • C0. General (26)
    • C1. Contamination (13)
    • C2. Copyright (120)
    • C3. Data Reconstruction (41)
    • C4. Membership Inference Attacks (32)
    • C5. Model Extraction (10)
    • C6. Privacy-Preserving Computation (63)
    • C7. Property Inference Attacks (3)
    • C8. Unlearning (45)

• 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