Awesome-LM-SSP and llm-sp

These are **complements** — one is a curated reading list/bibliography for LLM security research while the other is a focused repository of papers and resources, so users would typically consult both to build comprehensive knowledge of the field.

Awesome-LM-SSP
60
Established
llm-sp
43
Emerging
Maintenance 17/25
Adoption 10/25
Maturity 16/25
Community 17/25
Maintenance 2/25
Adoption 10/25
Maturity 16/25
Community 15/25
Stars: 1,882
Forks: 122
Downloads:
Commits (30d): 12
Language:
License: Apache-2.0
Stars: 570
Forks: 43
Downloads:
Commits (30d): 0
Language: Python
License: Apache-2.0
No Package No Dependents
Stale 6m No Package No Dependents

About Awesome-LM-SSP

CryptoAILab/Awesome-LM-SSP

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

This resource helps researchers and practitioners in the field of large models understand and mitigate risks related to safety, security, and privacy. It provides a curated reading list and database of research papers, books, competitions, and toolkits on topics like jailbreaking, adversarial attacks, and data privacy. Anyone working on or deploying large language, vision-language, or diffusion models would find this valuable.

AI Safety Model Security Data Privacy Large Language Models AI Ethics

About llm-sp

chawins/llm-sp

Papers and resources related to the security and privacy of LLMs 🤖

This resource curates and organizes research papers and materials focused on the security and privacy aspects of Large Language Models (LLMs). It helps security researchers, AI developers, and academic practitioners stay current with emerging threats like prompt injection and data privacy issues. The resource takes in a broad spectrum of research papers and provides a structured overview of vulnerabilities, defenses, and relevant datasets.

AI Security LLM Privacy Cybersecurity Research Prompt Engineering Vulnerability Analysis

Scores updated daily from GitHub, PyPI, and npm data. How scores work