Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/ThuCCSLab/Awesome-LM-SSP

A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).
https://github.com/ThuCCSLab/Awesome-LM-SSP

List: Awesome-LM-SSP

adversarial-attacks awesome-list diffusion-models jailbreak language-model llm nlp privacy safety security vlm

Last synced: 4 days ago
JSON representation

A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).

Host: GitHub
URL: https://github.com/ThuCCSLab/Awesome-LM-SSP
Owner: ThuCCSLab
License: apache-2.0
Created: 2024-01-09T04:17:50.000Z (10 months ago)
Default Branch: main
Last Pushed: 2024-10-24T08:35:25.000Z (16 days ago)
Last Synced: 2024-10-25T00:16:27.455Z (15 days ago)
Topics: adversarial-attacks, awesome-list, diffusion-models, jailbreak, language-model, llm, nlp, privacy, safety, security, vlm
Homepage: https://github.com/ThuCCSLab/Awesome-LM-SSP
Size: 2.14 MB
Stars: 871
Watchers: 23
Forks: 54
Open Issues: 2
Metadata Files:
- Readme: README.md
- License: LICENSE

Awesome Lists containing this project

Awesome-Jailbreak-on-LLMs - Awesome-LM-SSP
Awesome-LLM-Safety - link
awesome_LLM-harmful-fine-tuning-papers - Awesome LLM-SSP

README

        # Awesome-LM-SSP

[![Awesome](https://awesome.re/badge.svg)](https://awesome.re)

[![Page Views](https://badges.toozhao.com/badges/01HMRJE3211AJ2QD2X9AKTQG67/blue.svg)](.)

[![Stars](https://img.shields.io/github/stars/ThuCCSLab/Awesome-LM-SSP)](.)

[](.)

## 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:

        - ![LLM](https://img.shields.io/badge/LLM_(Large_Language_Model)-589cf4)

        - ![VLM](https://img.shields.io/badge/VLM_(Vision_Language_Model)-c7688b) 

        - ![SLM](https://img.shields.io/badge/SLM_(Speech_Language_Model)-39c5bb) 

        - ![Diffusion](https://img.shields.io/badge/Diffusion-a99cf4)

    - 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) ...

   - 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) ...

- :sunflower: Welcome to recommend resources to us via   Issues with the following format (**please fill in this table**): 

| Title | Link  | Code |   Venue |  Classification |  Model | Comment | 

| ---- |---- |---- |---- |---- |----|----| 

| aa |  arxiv | github  | bb'23    |  A1. Jailbreak | LLM  | Agent | 

## News

- [2024.08.17] We collected `34` related papers from [ACL'24](https://2024.aclweb.org/)!

- [2024.05.13] We collected `7` related papers from [S&P'24](https://www.computer.org/csdl/proceedings/sp/2024/1RjE8VKKk1y)!

- [2024.04.27] We adjusted the categories.

- [2024.01.20] We collected `3` related papers from [NDSS'24](https://www.ndss-symposium.org/ndss2024/accepted-papers/)!

- [2024.01.17] We collected `108` related papers from [ICLR'24](https://openreview.net/group?id=ICLR.cc/2024/Conference)!

- [2024.01.09] 🚀 LM-SSP is released!

## Collections

- [Book](collection/book.md) (2)

- [Competition](collection/competition.md) (5)

- [Leaderboard](collection/leaderboard.md) (3)

- [Toolkit](collection/toolkit.md) (9)

- [Survey](collection/survey.md) (32)

- Paper (1191)

    - A. Safety (670)

        - [A0. General](collection/paper/safety/general.md) (15)

        - [A1. Jailbreak](collection/paper/safety/jailbreak.md) (258)

        - [A2. Alignment](collection/paper/safety/alignment.md) (73)

        - [A3. Deepfake](collection/paper/safety/deepfake.md) (54)

        - [A4. Ethics](collection/paper/safety/ethics.md) (5)

        - [A5. Fairness](collection/paper/safety/fairness.md) (54)

        - [A6. Hallucination](collection/paper/safety/hallucination.md) (108)

        - [A7. Prompt Injection](collection/paper/safety/prompt_injection.md) (37)

        - [A8. Toxicity](collection/paper/safety/toxicity.md) (66)

    - B. Security (181)

        - [B0. General](collection/paper/security/general.md) (6)

        - [B1. Adversarial Examples](collection/paper/security/adversarial_examples.md) (79)

        - [B2. Poison & Backdoor](collection/paper/security/poison_&_backdoor.md) (86)

        - [B3. System](collection/paper/security/system.md) (10)

    - C. Privacy (340)

        - [C0. General](collection/paper/privacy/general.md) (24)

        - [C1. Contamination](collection/paper/privacy/contamination.md) (13)

        - [C2. Copyright](collection/paper/privacy/copyright.md) (115)

        - [C3. Data Reconstruction](collection/paper/privacy/data_reconstruction.md) (39)

        - [C4. Membership Inference Attacks](collection/paper/privacy/membership_inference_attacks.md) (31)

        - [C5. Model Extraction](collection/paper/privacy/model_extraction.md) (10)

        - [C6. Privacy-Preserving Computation](collection/paper/privacy/privacy-preserving_computation.md) (60)

        - [C7. Property Inference Attacks](collection/paper/privacy/property_inference_attacks.md) (3)

        - [C8. Unlearning](collection/paper/privacy/unlearning.md) (45)

## Star History

[![Star History Chart](https://api.star-history.com/svg?repos=ThuCCSLab/Awesome-LM-SSP&type=Date)](https://star-history.com/#ThuCCSLab/Awesome-LM-SSP&Date)

## Acknowledgement

- 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)

- This project is inspired by [LLM Security](https://llmsecurity.net/), [Awesome LLM Security](https://github.com/corca-ai/awesome-llm-security), [LLM Security & 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)