verazuo/jailbreak_llms

• highreadme#1

  Reposition README's opening to emphasize dataset identity

  原因：

  当前

  This is the official repository for the ACM CCS 2024 paper "Do Anything Now'': Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models by Xinyue Shen, Zeyuan Chen, Michael Backes, Yun Shen, and Yang Zhang.

  复制粘贴的修复

  复制

  This repository presents **JailbreakHub**, the largest dataset of in-the-wild jailbreak prompts on LLMs, as detailed in our ACM CCS 2024 paper "Do Anything Now'': Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models by Xinyue Shen, Zeyuan Chen, Michael Backes, Yun Shen, and Yang Zhang.

  待办完成忽略
• mediumtopics#2

  Add 'dataset' to repository topics

  原因：

  当前

  chatgpt, jailbreak, jailbreaking, large-language-model, llm, llm-security, prompt

  复制粘贴的修复

  复制

  chatgpt, jailbreak, jailbreaking, large-language-model, llm, llm-security, prompt, dataset

  待办完成忽略
• lowtopics#3

  Add 'benchmark' to repository topics

  原因：

  当前

  chatgpt, jailbreak, jailbreaking, large-language-model, llm, llm-security, prompt, dataset

  复制粘贴的修复

  复制

  chatgpt, jailbreak, jailbreaking, large-language-model, llm, llm-security, prompt, dataset, benchmark

  待办完成忽略

本次扫描解析到的品类 GEO 通道：google/gemini-2.5-flash, deepseek/deepseek-v4-flash

• 品类问题

  Looking for a dataset of prompts to analyze LLM jailbreaking techniques.

  你：未被推荐
  AI 推荐顺序：

  1. AdvBench (Adversarial Benchmark for LLMs)
  2. JailbreakBench
  3. HarmBench
  4. Red Teaming Language Models with Language Models (RLM-RLM) Dataset
  5. OpenAssistant Conversations Dataset (OASST1)
  6. Anthropic's Red Teaming Datasets

  AI 推荐了 6 个替代方案，却始终没点名 verazuo/jailbreak_llms。这就是要补上的差距。

  查看 AI 完整回答
• 品类问题

  What resources exist to study common large language model prompt bypasses?

  你：未被推荐
  AI 推荐顺序：

  1. OWASP Top 10 for Large Language Model Applications
  2. Gandalf
  3. Prompt Engineering Guide
  4. Hugging Face's "Prompt Engineering" Course

  AI 推荐了 4 个替代方案，却始终没点名 verazuo/jailbreak_llms。这就是要补上的差距。

  查看 AI 完整回答

• Metadata completeness

  pass

• README presence

  pass

• Compared to common alternatives in this category, what is the core differentiator of verazuo/jailbreak_llms?

  pass
  ✓AI 明确点名了 verazuo/jailbreak_llms

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？

• If a team adopts verazuo/jailbreak_llms in production, what risks or prerequisites should they evaluate first?

  pass
  ✓AI 明确点名了 verazuo/jailbreak_llms

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？

• In one sentence, what problem does the repo verazuo/jailbreak_llms solve, and who is the primary audience?

  pass
  ✓AI 明确点名了 verazuo/jailbreak_llms

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？