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:

    • 
    • 
    • 
    • 

  • Comment: ...

  • Venue: ...

• 🔥🔥🔥 Help us update the list! 🔥🔥🔥

  • First, check papers through our database: Metadata of LM-SSP.
  • 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 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

• [2026.01.09] 🎂🎂 Happy 2nd Birthday to Awesome-LM-SSP! Keep Going! 💪
• [2025.01.09] 🎂 Happy 1st Birthday to Awesome-LM-SSP! Keep Going! 💪
• [2024.01.09] 🚀 LM-SSP is released!

Collections

• Book (3)
• Competition (5)
• Leaderboard (5)
• Toolkit (33)
• Survey (42)
• Paper (2467)
  • A. Safety (1207)
    • A0. General (30)
    • A1. Jailbreak (545)
    • A2. Alignment (148)
    • A3. Deepfake (94)
    • A4. Ethics (8)
    • A5. Fairness (60)
    • A6. Hallucination (118)
    • A7. Prompt Injection (118)
    • A8. Toxicity (86)
  • B. Security (521)
    • B0. General (16)
    • B1. Adversarial Examples (105)
    • B2. Adversarial Examples (1)
    • B3. Agent (162)
    • B4. Poison & Backdoor (193)
    • B5. Prompt Injection (12)
    • B6. Side-Channel (6)
    • B7. System (26)
  • C. Privacy (739)
    • C0. General (55)
    • C1. Contamination (17)
    • C2. Data Reconstruction (69)
    • C3. Membership Inference Attacks (73)
    • C4. Model Extraction (15)
    • C5. Privacy-Preserving Computation (135)
    • C6. Property Inference Attacks (9)
    • C7. Side-Channel (10)
    • C8. Unlearning (70)
    • C9. Watermark & Copyright (286)

Big love to the community — thank you! 🙏

Acknowledgement

• 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