Alternatives and similar repositories for jailbreak-bench:

Users that are interested in jailbreak-bench are comparing it to the libraries listed below

• HKUST-KnowComp / LLM-Multistep-Jailbreak
  Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT
  ☆33Updated last year
• NY1024 / Foundation-Model-Paper-Notes
  ☆52Updated 4 months ago
• roywang021 / UMK
  Code for ACM MM2024 paper: White-box Multimodal Jailbreaks Against Large Vision-Language Models
  ☆26Updated 4 months ago
• ltroin / llm_attack_defense_arena
  ☆79Updated last year
• xirui-li / DrAttack
  Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers
  ☆52Updated 8 months ago
• WUSTL-CSPL / LLMJailbreak
  ☆31Updated 7 months ago
• ledllm / ledllm
  ☆18Updated 10 months ago
• kriti-hippo / red_queen
  Red Queen Dataset and data generation template
  ☆15Updated 7 months ago
• YancyKahn / CoA
  Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM
  ☆31Updated 3 months ago
• Lyz1213 / BadEdit
  ☆26Updated 6 months ago
• ThuCCSLab / FigStep
  [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts
  ☆136Updated 2 months ago
• theshi-1128 / llm-defense
  An easy-to-use Python framework to defend against jailbreak prompts.
  ☆20Updated last month
• AI45Lab / ActorAttack
  ☆82Updated 3 months ago
• bboylyg / BackdoorLLM
  BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks on Large Language Models
  ☆140Updated last week
• DPamK / BadAgent
  ☆17Updated 2 months ago
• Aatrox103 / SAP
  ☆44Updated last year
• lancopku / codable-watermarking-for-llm
  Repository for Towards Codable Watermarking for Large Language Models
  ☆36Updated last year
• Unispac / Visual-Adversarial-Examples-Jailbreak-Large-Language-Models
  Repository for the Paper (AAAI 2024, Oral) --- Visual Adversarial Examples Jailbreak Large Language Models
  ☆219Updated 11 months ago
• isXinLiu / MM-SafetyBench
  Accepted by ECCV 2024
  ☆127Updated 6 months ago
• SaFoLab-WISC / JailBreakV_28K
  [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…
  ☆58Updated 2 weeks ago
• tmllab / 2025_ICLR_PiF
  ☆23Updated 2 weeks ago
• xingjunm / Awesome-Large-Model-Safety
  Safety at Scale: A Comprehensive Survey of Large Model Safety
  ☆153Updated 2 months ago
• rotaryhammer / code-autodan
  An unofficial implementation of AutoDAN attack on LLMs (arXiv:2310.15140)
  ☆38Updated last year
• wang2226 / Trojan-Activation-Attack
  [CIKM 2024] Trojan Activation Attack: Attack Large Language Models using Activation Steering for Safety-Alignment.
  ☆23Updated 9 months ago
• neelsjain / baseline-defenses
  Official Code for "Baseline Defenses for Adversarial Attacks Against Aligned Language Models"
  ☆23Updated last year
• uw-nsl / ArtPrompt
  [ACL24] Official Repo of Paper `ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs`
  ☆68Updated 2 months ago
• theshi-1128 / ABJ-Attack
  LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models
  ☆19Updated last month
• huizhang-L / CodeChameleon
  ☆21Updated last year
• RICommunity / TAP
  TAP: An automated jailbreaking method for black-box LLMs
  ☆165Updated 5 months ago
• LLMSecurity / MasterKey
  MASTERKEY is a framework designed to explore and exploit vulnerabilities in large language model chatbots by automating jailbreak attacks…
  ☆21Updated 7 months ago