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

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

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

List: Awesome-LM-SSP

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

Last synced: 10 days ago
JSON representation

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

Awesome Lists containing this project

README

          

# Awesome-LM-SSP

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

[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: (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) ...

- ๐Ÿ”ฅ๐Ÿ”ฅ๐Ÿ”ฅ Help us update the list! ๐Ÿ”ฅ๐Ÿ”ฅ๐Ÿ”ฅ
- First, check papers through our database: [Metadata of LM-SSP](https://docs.google.com/spreadsheets/d/1i2IfQJiAdFJueoy7sTv7snn__ZJx11GfiJx8rhDyfc0/edit?usp=sharing).
- If you want to update the information of a paper (e.g., an arXiv paper has been accepted by a venue), search the paper title in our [metadata table](https://docs.google.com/spreadsheets/d/1i2IfQJiAdFJueoy7sTv7snn__ZJx11GfiJx8rhDyfc0/edit?usp=sharing) and then leave a message in the corresponding cell of the table.
- If you would like to add some paper, please fill in the following table through `ISSUE`:

| Title | Link | Code | Venue | Classification | Model | Comment |
| ---- |---- |---- |---- |---- |----|----|
| This is a title | paper.com | github | bb'23 | A1. Jailbreak | LLM | Agent |

## News
- [2025.01.09] ๐ŸŽ‚ Happy 1st Birthday to Awesome-LM-SSP! Keep Going! ๐Ÿ’ช
- [2024.01.09] ๐Ÿš€ LM-SSP is released!

## Collections
- [Book](collection/book.md) (3)
- [Competition](collection/competition.md) (5)
- [Leaderboard](collection/leaderboard.md) (5)
- [Toolkit](collection/toolkit.md) (14)
- [Survey](collection/survey.md) (40)
- Paper (2352)
- A. Safety (1183)
- [A0. General](collection/paper/safety/general.md) (30)
- [A1. Jailbreak](collection/paper/safety/jailbreak.md) (530)
- [A2. Alignment](collection/paper/safety/alignment.md) (145)
- [A3. Deepfake](collection/paper/safety/deepfake.md) (94)
- [A4. Ethics](collection/paper/safety/ethics.md) (8)
- [A5. Fairness](collection/paper/safety/fairness.md) (60)
- [A6. Hallucination](collection/paper/safety/hallucination.md) (116)
- [A7. Prompt Injection](collection/paper/safety/prompt_injection.md) (114)
- [A8. Toxicity](collection/paper/safety/toxicity.md) (86)
- B. Security (457)
- [B0. General](collection/paper/security/general.md) (16)
- [B1. Adversarial Examples](collection/paper/security/adversarial_examples.md) (105)
- [B2. Agent](collection/paper/security/agent.md) (132)
- [B3. Poison & Backdoor](collection/paper/security/poison_&_backdoor.md) (178)
- [B4. Side-Channel](collection/paper/security/side-channel.md) (2)
- [B5. System](collection/paper/security/system.md) (24)
- C. Privacy (712)
- [C0. General](collection/paper/privacy/general.md) (54)
- [C1. Contamination](collection/paper/privacy/contamination.md) (17)
- [C2. Data Reconstruction](collection/paper/privacy/data_reconstruction.md) (63)
- [C3. Membership Inference Attacks](collection/paper/privacy/membership_inference_attacks.md) (65)
- [C4. Model Extraction](collection/paper/privacy/model_extraction.md) (14)
- [C5. Privacy-Preserving Computation](collection/paper/privacy/privacy-preserving_computation.md) (131)
- [C6. Property Inference Attacks](collection/paper/privacy/property_inference_attacks.md) (8)
- [C7. Side-Channel](collection/paper/privacy/side-channel.md) (10)
- [C8. Unlearning](collection/paper/privacy/unlearning.md) (70)
- [C9. Watermark & Copyright](collection/paper/privacy/watermark_&_copyright.md) (280)

## Big love to the community โ€” thank you! ๐Ÿ™

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

## Acknowledgement

- Organizers: [Tianshuo Cong (ไธ›ๅคฉ็ก•)](https://tianshuocong.github.io/), [Xinlei He (ไฝ•ๆ–ฐ็ฃŠ)](https://xinleihe.github.io/), [Zhengyu Zhao (่ตตๆญฃๅฎ‡)](https://zhengyuzhao.github.io/), [Yugeng Liu (ๅˆ˜็ฆนๆ›ด)](https://liu.ai/), [Delong Ran (ๅ†‰ๅพท้พ™)](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)