Alternatives and similar repositories for JailBench

Users that are interested in JailBench are comparing it to the libraries listed below

• WhitzardIndex / WhitzardBench-2024A
  复旦白泽大模型安全基准测试集（2024年夏季版）
  ☆41Updated 11 months ago
• whitzard-ai / jade-db
  "他山之石、可以攻玉"：复旦白泽智能发布面向国内开源和国外商用大模型的Demo数据集JADE-DB
  ☆428Updated 2 weeks ago
• LLM-DRA / DRA
  [USENIX Security'24] Official repository of "Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise a…
  ☆99Updated 9 months ago
• CLUEbenchmark / SuperCLUE-Safety
  SC-Safety: 中文大模型多轮对抗安全基准
  ☆141Updated last year
• liu673 / Awesome-LLM4Security
  This project aims to consolidate and share high-quality resources and tools across the cybersecurity domain.
  ☆220Updated last week
• ddzipp / AutoAudit
  AutoAudit—— the LLM for Cyber Security 网络安全大语言模型
  ☆340Updated 4 months ago
• thu-coai / ShieldLM
  ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors [EMNLP 2024 Findings]
  ☆204Updated 9 months ago
• LLMSmith / LLMSmith
  ☆33Updated 4 months ago
• sherdencooper / GPTFuzz
  Official repo for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
  ☆504Updated 9 months ago
• OpenStellarTeam / ChineseSafetyQA
  ☆30Updated 6 months ago
• gitkolento / Adversarial-Attacks-on-LLMs
  针对大语言模型的对抗性攻击总结
  ☆31Updated last year
• y4ney / LLM-Security
  LLM 安全资料收集与学习
  ☆24Updated last year
• 1700111005 / autoMSS
  AutoMSS 是基于AI Agent实现的针对安全事件自动化分析研判的系统，由cloud Totem团队开发，希望有兴趣的朋友可以一起参与进来更新和完善。邮箱联系：automss@cloud-totem.com
  ☆47Updated last year
• sherdencooper / PromptFuzz
  ☆26Updated 8 months ago
• xingjunm / Awesome-Large-Model-Safety
  Safety at Scale: A Comprehensive Survey of Large Model Safety
  ☆183Updated 4 months ago
• xu-xiang / awesome-security-vul-llm
  本项目通过大模型联动爬虫，检索Github上所有存有有价值漏洞信息与漏洞POC或规则信息的项目，并自动识别项目的目录结构、Readme信息后进行总结分析并分类，所汇总的项目可以帮助安全行业从业者收集漏洞信息、POC信息、规则等。
  ☆135Updated last year
• RiskySignal / record_what_i_read
  AI Model Security Reading Notes
  ☆39Updated 4 months ago
• XuanwuAI / SecEval
  ☆99Updated last year
• thu-coai / SafetyBench
  Official github repo for SafetyBench, a comprehensive benchmark to evaluate LLMs' safety. [ACL 2024]
  ☆228Updated last year
• Clouditera / Clouditera.github.io
  塑造未来的安全领域智能革命
  ☆627Updated 5 months ago
• thu-coai / Safety-Prompts
  Chinese safety prompts for evaluating and improving the safety of LLMs. 中文安全prompts，用于评估和提升大模型的安全性。
  ☆1,048Updated last year
• mxcrafts / ltrack
  Security Observability Framework for ML/AI Model File Loading
  ☆35Updated 3 weeks ago
• CS-EVAL / CS-Eval
  CS-Eval is a comprehensive evaluation suite for fundamental cybersecurity models or large language models' cybersecurity ability.
  ☆43Updated 7 months ago
• TrustAI-laboratory / Learn-Prompt-Hacking
  This is The most comprehensive prompt hacking course available, which record our progress on a prompt engineering and prompt hacking cour…
  ☆88Updated 3 months ago
• deepsec-top / deepsec
  中文网络安全运营领域开源语料库
  ☆30Updated last month
• SecureNexusLab / LLMPromptAttackGuide
  ☆142Updated 9 months ago
• EasyJailbreak / EasyJailbreak
  An easy-to-use Python framework to generate adversarial jailbreak prompts.
  ☆680Updated 3 months ago
• Aatrox103 / SAP
  ☆45Updated last year
• RockyHHH / Safety-Evaluating
  本文提出了一个基于“文心一言”的中国LLMs的安全评估基准，其中包括8种典型的安全场景和6种指令攻击类型。此外，本文还提出了安全评估的框架和过程，利用手动编写和收集开源数据的测试Prompts，以及人工干预结合利用LLM强大的评估能力作为“共同评估者”。
  ☆26Updated last year
• agiresearch / ASB
  Agent Security Bench (ASB)
  ☆94Updated last month