Alternatives and similar repositories for SoK4JailbreakGuardrails

Users that are interested in SoK4JailbreakGuardrails are comparing it to the libraries listed below

• Aegis1863 / xJailbreak
  Code of paper: xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking"
  ☆14Updated 6 months ago
• aaFrostnova / Papillon
  [Usenix Security 2025] Official repo of paper PAPILLON: Efficient and Stealthy Fuzz Testing-Powered Jailbreaks for LLMs
  ☆15Updated 4 months ago
• theshi-1128 / jailbreak-bench
  The most comprehensive and accurate LLM jailbreak attack benchmark by far
  ☆21Updated 6 months ago
• KutalVolkan / many-shot-jailbreaking-dataset
  Q&A dataset for many-shot jailbreaking
  ☆11Updated last year
• shadowkiller33 / Language_attack
  A repo for LLM jailbreak
  ☆14Updated 2 years ago
• UNHSAILLab / working-memory-attack-on-llms
  Working Memory Attack on LLMs
  ☆16Updated 4 months ago
• Vinsonzyh / BlueSuffix
  [ICLR 2025] BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks
  ☆22Updated 5 months ago
• uw-nsl / ArtPrompt
  [ACL24] Official Repo of Paper `ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs`
  ☆85Updated last month
• LLM-DRA / DRA
  [USENIX Security'24] Official repository of "Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise a…
  ☆108Updated 11 months ago
• NJUNLP / ReNeLLM
  The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Lang…
  ☆137Updated last month
• Helloworld10011 / Adversarial-Reasoning
  A new algorithm that formulates jailbreaking as a reasoning problem.
  ☆25Updated 3 months ago
• facebookresearch / multimodal-fusion-jailbreaks
  Official repository for the paper "Gradient-based Jailbreak Images for Multimodal Fusion Models" (https//arxiv.org/abs/2410.03489)
  ☆19Updated 11 months ago
• xirui-li / DrAttack
  Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers
  ☆62Updated last year
• kztakemoto / simbaja
  All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks
  ☆18Updated last year
• Ymm-cll / TrustAgent
  ☆62Updated 6 months ago
• mbzuai-nlp / AudioJailbreak
  Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models
  ☆20Updated 4 months ago
• TrustAI-laboratory / Many-Shot-Jailbreaking-Demo
  Research on "Many-Shot Jailbreaking" in Large Language Models (LLMs). It unveils a novel technique capable of bypassing the safety mechan…
  ☆14Updated last year
• NY1024 / Jailbreak_GPT4o
  ☆24Updated last year
• NLie2 / what_features_jailbreak_LLMs
  ☆17Updated 6 months ago
• RylanSchaeffer / AstraFellowship-When-Do-VLM-Image-Jailbreaks-Transfer
  Code for ICLR 2025 Failures to Find Transferable Image Jailbreaks Between Vision-Language Models
  ☆31Updated 4 months ago
• AI45Lab / X-Boundary
  The code repo of paper "X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Multi-Turn Jailbreaks without Compromising Usa…
  ☆35Updated 6 months ago
• Allen-piexl / JailbreakZoo
  ☆149Updated last year
• ThuCCSLab / FigStep
  [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts
  ☆173Updated 3 months ago
• tmlr-group / DeepInception
  [arXiv:2311.03191] "DeepInception: Hypnotize Large Language Model to Be Jailbreaker"
  ☆163Updated last year
• agiresearch / ASB
  Agent Security Bench (ASB)
  ☆124Updated this week
• thunxxx / MLLM-Jailbreak-evaluation-MMJ-Bench
  ☆63Updated 6 months ago
• EasyJailbreak / EasyJailbreak
  An easy-to-use Python framework to generate adversarial jailbreak prompts.
  ☆724Updated 6 months ago
• PKU-YuanGroup / Hallucination-Attack
  Attack to induce LLMs within hallucinations
  ☆157Updated last year
• GodXuxilie / PromptAttack
  An LLM can Fool Itself: A Prompt-Based Adversarial Attack (ICLR 2024)
  ☆99Updated 8 months ago
• AoiDragon / HADES
  [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …
  ☆36Updated 11 months ago