Awesome
Awesome-LM-SSP
<img src="figure/title_new.png" alt="Awesome-LM-SSP" width="1000" height="auto" class="center">
Introduction
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 :seedling: (currently manually collected).
-
Badges:
-
Model:
-
Comment:
...
-
Venue:
...
-
-
:sunflower: Welcome to recommend resources to us via <a href="https://github.com/ThuCCSLab/Awesome-LM-SSP/issues"> <img src="https://icons.iconarchive.com/icons/github/octicons/128/issue-opened-16-icon.png" width="15" height="15"></a> Issues with the following format (please fill in this table):
-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 |
News
- [2024.08.17] We collected
34related papers from ACL'24! - [2024.05.13] We collected
7related papers from S&P'24! - [2024.04.27] We adjusted the categories.
- [2024.01.20] We collected
3related papers from NDSS'24! - [2024.01.17] We collected
108related papers from ICLR'24! - [2024.01.09] 🚀 LM-SSP is released!
Collections
- Book (2)
- Competition (5)
- Leaderboard (3)
- Toolkit (9)
- Survey (31)
- Paper (1045)
- A. Safety (604)
- A0. General (15)
- A1. Jailbreak (227)
- A2. Alignment (65)
- A3. Deepfake (51)
- A4. Ethics (5)
- A5. Fairness (53)
- A6. Hallucination (105)
- A7. Prompt Injection (21)
- A8. Toxicity (62)
- B. Security (163)
- B0. General (5)
- B1. Adversarial Examples (75)
- B2. Poison & Backdoor (75)
- B3. System (8)
- C. Privacy (278)
- C0. General (23)
- C1. Contamination (13)
- C2. Copyright (90)
- C3. Data Reconstruction (32)
- C4. Membership Inference Attacks (23)
- C5. Model Extraction (9)
- C6. Privacy-Preserving Computation (44)
- C7. Property Inference Attacks (3)
- C8. Unlearning (41)
- A. Safety (604)
Star History
Acknowledgement
-
Organizers: Tianshuo Cong (丛天硕), Xinlei He (何新磊), Zhengyu Zhao (èµµæ£å®‡), 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