yueliu1999/Awesome-Jailbreak-on-LLMs resource

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1602 stars · 126 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A curated awesome-list collecting state-of-the-art jailbreak methods on large language models, including papers, code, datasets, evaluations, and analyses. It covers jailbreak attacks (black-box, white-box, multi-turn, multi-modal, on LRMs and RAG-based LLMs) and defenses such as guard models and moderation APIs.

Use cases

• find recent papers on LLM jailbreak attacks
• research red-teaming techniques for large language models
• find datasets for evaluating LLM safety
• compare jailbreak defense methods and guard models
• survey multi-modal jailbreak attacks on vision-language models
• find open-source implementations of jailbreak attacks

When to choose

• you are researching LLM safety, adversarial attacks, or guardrails
• you need a curated starting point for jailbreak literature and code
• you want to benchmark or evaluate LLM robustness against attacks

When to avoid

• you need a production tool or library rather than a paper collection
• you want a general LLM safety resource not focused on jailbreaks
• you need a maintained software package with APIs

Facets

learning-resource · maturity active

security nlp machine-learning large-language-models security artificial-intelligence awesome-lists cross-platform jailbreak llm-safety awesome-list red-teaming adversarial-attacks guardrails vlm

Member repositories

For agents

markdown · JSON · MCP: product_card(name="yueliu1999/Awesome-Jailbreak-on-LLMs")