{"id":13562512,"url":"https://github.com/ThuCCSLab/Awesome-LM-SSP","last_synced_at":"2025-04-03T18:33:47.229Z","repository":{"id":216229649,"uuid":"740789348","full_name":"ThuCCSLab/Awesome-LM-SSP","owner":"ThuCCSLab","description":"A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).","archived":false,"fork":false,"pushed_at":"2024-10-24T08:35:25.000Z","size":2241,"stargazers_count":871,"open_issues_count":2,"forks_count":54,"subscribers_count":23,"default_branch":"main","last_synced_at":"2024-10-25T00:16:27.455Z","etag":null,"topics":["adversarial-attacks","awesome-list","diffusion-models","jailbreak","language-model","llm","nlp","privacy","safety","security","vlm"],"latest_commit_sha":null,"homepage":"https://github.com/ThuCCSLab/Awesome-LM-SSP","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ThuCCSLab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-01-09T04:17:50.000Z","updated_at":"2024-10-24T15:22:33.000Z","dependencies_parsed_at":"2024-06-27T05:27:14.289Z","dependency_job_id":"81cafa1a-f3a9-435b-80ed-5a5f3ffd8576","html_url":"https://github.com/ThuCCSLab/Awesome-LM-SSP","commit_stats":{"total_commits":351,"total_committers":8,"mean_commits":43.875,"dds":0.5925925925925926,"last_synced_commit":"645991c7def226856bd6646af5f7b41874dc1439"},"previous_names":["thuccslab/lm-ssp","thuccslab/awesome-lm-ssp"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ThuCCSLab%2FAwesome-LM-SSP","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ThuCCSLab%2FAwesome-LM-SSP/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ThuCCSLab%2FAwesome-LM-SSP/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ThuCCSLab%2FAwesome-LM-SSP/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ThuCCSLab","download_url":"https://codeload.github.com/ThuCCSLab/Awesome-LM-SSP/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247057097,"owners_count":20876512,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["adversarial-attacks","awesome-list","diffusion-models","jailbreak","language-model","llm","nlp","privacy","safety","security","vlm"],"created_at":"2024-08-01T13:01:09.425Z","updated_at":"2025-04-03T18:33:42.197Z","avatar_url":"https://github.com/ThuCCSLab.png","language":null,"funding_links":[],"categories":["Others","Other Related Awesome Repository","[↑](#table-of-contents)Related Awesome Lists \u003ca name=\"related-awesome-lists\"\u003e\u003c/a\u003e","Content","A01_文本生成_文本对话","🔏Privacy"],"sub_categories":["Application","Startup Blogs \u003ca name=\"startup-blogs\"\u003e\u003c/a\u003e","Other awesome resources on LLM safety","大语言对话模型及数据","📖Tutorials, Articles, Presentations and Talks"],"readme":"# Awesome-LM-SSP\n\n[![Awesome](https://awesome.re/badge.svg)](https://awesome.re)\n[![Page Views](https://badges.toozhao.com/badges/01HMRJE3211AJ2QD2X9AKTQG67/blue.svg)](.)\n[![Stars](https://img.shields.io/github/stars/ThuCCSLab/Awesome-LM-SSP)](.)\n\n[\u003cimg src=\"figure/title_new.png\" alt=\"Awesome-LM-SSP\" width=\"1000\" height=\"auto\" class=\"center\"\u003e](.)\n\n## Introduction \nThe 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). \n\n- This repo is in progress :seedling: (currently manually collected).\n- Badges: \n\n    - Model:\n        - ![LLM](https://img.shields.io/badge/LLM_(Large_Language_Model)-589cf4)\n        - ![VLM](https://img.shields.io/badge/VLM_(Vision_Language_Model)-c7688b) \n        - ![SLM](https://img.shields.io/badge/SLM_(Speech_Language_Model)-39c5bb) \n        - ![Diffusion](https://img.shields.io/badge/Diffusion-a99cf4)\n\n    - Comment: ![Benchmark](https://img.shields.io/badge/Benchmark-87b800) ![New_dataset](https://img.shields.io/badge/New_dataset-87b800) ![Agent](https://img.shields.io/badge/Agent-87b800)                 ![CodeGen](https://img.shields.io/badge/CodeGen-87b800) ![Defense](https://img.shields.io/badge/Defense-87b800) ![RAG](https://img.shields.io/badge/RAG-87b800) ![Chinese](https://img.shields.io/badge/Chinese-87b800) ...\n\n   - Venue: ![conference](https://img.shields.io/badge/conference-f1b800) ![blog](https://img.shields.io/badge/blog-f1b800) ![OpenAI](https://img.shields.io/badge/OpenAI-f1b800)  ![Meta AI](https://img.shields.io/badge/Meta_AI-f1b800) ...\n\n- :sunflower: Welcome to recommend resources to us via \u003ca href=\"https://github.com/ThuCCSLab/Awesome-LM-SSP/issues\"\u003e \u003cimg src=\"https://icons.iconarchive.com/icons/github/octicons/128/issue-opened-16-icon.png\" width=\"15\" height=\"15\"\u003e\u003c/a\u003e Issues with the following format (**please fill in this table**): \n\n| Title | Link  | Code |   Venue |  Classification |  Model | Comment | \n| ---- |---- |---- |---- |---- |----|----| \n| aa |  arxiv | github  | bb'23    |  A1. Jailbreak | LLM  | Agent | \n\n## News\n- [2024.08.17] We collected `34` related papers from [ACL'24](https://2024.aclweb.org/)!\n- [2024.05.13] We collected `7` related papers from [S\u0026P'24](https://www.computer.org/csdl/proceedings/sp/2024/1RjE8VKKk1y)!\n- [2024.04.27] We adjusted the categories.\n- [2024.01.20] We collected `3` related papers from [NDSS'24](https://www.ndss-symposium.org/ndss2024/accepted-papers/)!\n- [2024.01.17] We collected `108` related papers from [ICLR'24](https://openreview.net/group?id=ICLR.cc/2024/Conference)!\n- [2024.01.09] 🚀 LM-SSP is released!\n\n## Collections\n- [Book](collection/book.md) (2)\n- [Competition](collection/competition.md) (5)\n- [Leaderboard](collection/leaderboard.md) (3)\n- [Toolkit](collection/toolkit.md) (9)\n- [Survey](collection/survey.md) (32)\n- Paper (1191)\n    - A. Safety (670)\n        - [A0. General](collection/paper/safety/general.md) (15)\n        - [A1. Jailbreak](collection/paper/safety/jailbreak.md) (258)\n        - [A2. Alignment](collection/paper/safety/alignment.md) (73)\n        - [A3. Deepfake](collection/paper/safety/deepfake.md) (54)\n        - [A4. Ethics](collection/paper/safety/ethics.md) (5)\n        - [A5. Fairness](collection/paper/safety/fairness.md) (54)\n        - [A6. Hallucination](collection/paper/safety/hallucination.md) (108)\n        - [A7. Prompt Injection](collection/paper/safety/prompt_injection.md) (37)\n        - [A8. Toxicity](collection/paper/safety/toxicity.md) (66)\n    - B. Security (181)\n        - [B0. General](collection/paper/security/general.md) (6)\n        - [B1. Adversarial Examples](collection/paper/security/adversarial_examples.md) (79)\n        - [B2. Poison \u0026 Backdoor](collection/paper/security/poison_\u0026_backdoor.md) (86)\n        - [B3. System](collection/paper/security/system.md) (10)\n    - C. Privacy (340)\n        - [C0. General](collection/paper/privacy/general.md) (24)\n        - [C1. Contamination](collection/paper/privacy/contamination.md) (13)\n        - [C2. Copyright](collection/paper/privacy/copyright.md) (115)\n        - [C3. Data Reconstruction](collection/paper/privacy/data_reconstruction.md) (39)\n        - [C4. Membership Inference Attacks](collection/paper/privacy/membership_inference_attacks.md) (31)\n        - [C5. Model Extraction](collection/paper/privacy/model_extraction.md) (10)\n        - [C6. Privacy-Preserving Computation](collection/paper/privacy/privacy-preserving_computation.md) (60)\n        - [C7. Property Inference Attacks](collection/paper/privacy/property_inference_attacks.md) (3)\n        - [C8. Unlearning](collection/paper/privacy/unlearning.md) (45)\n\n## Star History\n\n[![Star History Chart](https://api.star-history.com/svg?repos=ThuCCSLab/Awesome-LM-SSP\u0026type=Date)](https://star-history.com/#ThuCCSLab/Awesome-LM-SSP\u0026Date)\n\n## Acknowledgement\n\n- Organizers: [Tianshuo Cong (丛天硕)](https://tianshuocong.github.io/), [Xinlei He (何新磊)](https://xinleihe.github.io/), [Zhengyu Zhao (赵正宇)](https://zhengyuzhao.github.io/), [Yugeng Liu (刘禹更)](https://liu.ai/), [Delong Ran (冉德龙)](https://github.com/eggry)\n\n- This project is inspired by [LLM Security](https://llmsecurity.net/), [Awesome LLM Security](https://github.com/corca-ai/awesome-llm-security), [LLM Security \u0026 Privacy](https://github.com/chawins/llm-sp),             [UR2-LLMs](https://github.com/jxzhangjhu/Awesome-LLM-Uncertainty-Reliability-Robustness), [PLMpapers](https://github.com/thunlp/PLMpapers), [EvaluationPapers4ChatGPT](https://github.com/THU-KEG/EvaluationPapers4ChatGPT)\n\n\u003cp align=\"center\"\u003e\u003cimg src=\"figure/logo.png\" width=\"900\" /\u003e\u003c/p\u003e","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FThuCCSLab%2FAwesome-LM-SSP","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FThuCCSLab%2FAwesome-LM-SSP","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FThuCCSLab%2FAwesome-LM-SSP/lists"}