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 (Continuous update): or

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

• [2023.01.20] 🔥 We collect 3 related papers from NDSS'24!
• [2023.01.17] 🔥 We collect 108 related papers from ICLR'24!
• [2023.01.09] 🔥 LM-SSP is released!

• Book (1)
• Competition (5)
• Leaderboard (3)
• Toolkit (3)
• Survey (23)
• Paper
  • A. Safety
    • A1. Jailbreak (107)
    • A2. Alignment (43)
    • A3. Deepfake (26)
    • A4. Ethics (5)
    • A5. Fairness (44)
    • A6. Hallucination (83)
    • A7. Prompt Injection (6)
    • A8. Toxicity (40)
  • B. Security
    • B1. Adversarial Examples (52)
    • B2. Poisoning (35)
    • B3. System (3)
  • C. Privacy
    • C1. Contamination (6)
    • C2. Copyright (31)
    • C3. Data Reconstruction (10)
    • C4. Extraction (5)
    • C5. Inference (23)
    • C6. Privacy-Preserving Computation (15)
    • C7. Unlearning (18)

• 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