Alternatives and similar repositories for Jailbreak-In-Pieces

Users that are interested in Jailbreak-In-Pieces are comparing it to the libraries listed below

• thunxxx / MLLM-Jailbreak-evaluation-MMJ-Bench
  ☆66Updated 9 months ago
• CryptoAILab / FigStep
  [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts
  ☆184Updated 6 months ago
• isXinLiu / MM-SafetyBench
  Accepted by ECCV 2024
  ☆179Updated last year
• ys-zong / VLGuard
  [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.
  ☆82Updated 11 months ago
• abc03570128 / Jailbreaking-Attack-against-Multimodal-Large-Language-Model
  ☆55Updated last year
• RUCAIBox / HADES
  [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …
  ☆33Updated last year
• Haochen-Luo / CroPA
  ☆54Updated last year
• NY1024 / BAP-Jailbreak-Vision-Language-Models-via-Bi-Modal-Adversarial-Prompt
  ☆55Updated last year
• SaFo-Lab / JailBreakV_28K
  [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…
  ☆84Updated 7 months ago
• umd-huang-lab / VLM-Poisoning
  Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"
  ☆58Updated 11 months ago
• ASTRAL-Group / ASTRA
  [CVPR 2025] Official implementation for "Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbre…
  ☆47Updated 5 months ago
• SaFo-Lab / AdaShield
  [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shi…
  ☆67Updated last year
• AoiDragon / HADES
  [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …
  ☆36Updated last year
• euanong / image-hijacks
  Official codebase for Image Hijacks: Adversarial Images can Control Generative Models at Runtime
  ☆55Updated 2 years ago
• thu-ml / MMTrustEval
  A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)
  ☆173Updated 6 months ago
• ericyinyzy / VLAttack
  This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2…
  ☆63Updated 9 months ago
• roywang021 / IDEATOR
  Code for ICCV2025 paper——IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves
  ☆14Updated 5 months ago
• huanranchen / VLMTransfer
  A package that achieves 95%+ transfer attack success rate against GPT-4
  ☆25Updated last year
• tmllab / 2025_ICLR_PiF
  ☆37Updated 7 months ago
• gyhdog99 / ECSO
  ECSO (Make MLLM safe without neither training nor any external models!) (https://arxiv.org/abs/2403.09572)
  ☆36Updated last year
• roywang021 / UMK
  Code for ACM MM2024 paper: White-box Multimodal Jailbreaks Against Large Vision-Language Models
  ☆31Updated last year
• Vinsonzyh / BlueSuffix
  [ICLR 2025] BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks
  ☆30Updated 2 months ago
• thu-ml / Attack-Bard
  ☆107Updated last year
• itsvaibhav01 / Immune
  [CVPR2025] Official Repository for IMMUNE: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment
  ☆26Updated 6 months ago
• Sadcardation / MLLM-Refusal
  Repository for the Paper: Refusing Safe Prompts for Multi-modal Large Language Models
  ☆18Updated last year
• YitingQu / unsafe-diffusion
  ☆42Updated last year
• AI45Lab / VLSBench
  [ACL 2025] Data and Code for Paper VLSBench: Unveiling Visual Leakage in Multimodal Safety
  ☆52Updated 5 months ago
• AI-secure / MMDT
  Comprehensive Assessment of Trustworthiness in Multimodal Foundation Models
  ☆25Updated 9 months ago
• wangyu-ovo / MML
  Code for the paper "Jailbreak Large Vision-Language Models Through Multi-Modal Linkage"
  ☆25Updated last year
• isXinLiu / Awesome-MLLM-Safety
  Accepted by IJCAI-24 Survey Track
  ☆225Updated last year