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 🌱 (manually collected).
-
Badges:
-
Model:
-
Comment:
...
-
Venue:
...
-
-
🌻 Welcome to recommend resources to us via pulling requests or opening issues with the following format:
-589cf4){kind=icon}
-c7688b){kind=icon}
-39c5bb){kind=icon}
| Title | Link | Code | Venue | Classification | Model | Comment |
|---|---|---|---|---|---|---|
| aa | arxiv | github | bb'23 | A1. Jailbreak | LLM | Agent |
- [2025.01.09] 🎂 Happy 1st Birthday to Awesome-LM-SSP! Keep Going! 💪
- [2024.01.09] 🚀 LM-SSP is released!
- Book (3)
- Competition (5)
- Leaderboard (5)
- Toolkit (13)
- Survey (40)
- Paper (2283)
- A. Safety (1153)
- A0. General (29)
- A1. Jailbreak (517)
- A2. Alignment (140)
- A3. Deepfake (91)
- A4. Ethics (8)
- A5. Fairness (60)
- A6. Hallucination (116)
- A7. Prompt Injection (107)
- A8. Toxicity (85)
- B. Security (437)
- B0. General (14)
- B1. Adversarial Examples (102)
- B2. Agent (124)
- B3. Poison & Backdoor (173)
- B4. Side-Channel (1)
- B5. System (23)
- C. Privacy (693)
- C0. General (53)
- C1. Contamination (17)
- C2. Data Reconstruction (63)
- C3. Membership Inference Attacks (61)
- C4. Model Extraction (14)
- C5. Privacy-Preserving Computation (128)
- C6. Property Inference Attacks (7)
- C7. Side-Channel (10)
- C8. Unlearning (67)
- C9. Watermark & Copyright (273)
- A. Safety (1153)
-
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
