NY1024 / BAP-Jailbreak-Vision-Language-Models-via-Bi-Modal-Adversarial-Prompt

Related projects ⓘ

Alternatives and complementary repositories for BAP-Jailbreak-Vision-Language-Models-via-Bi-Modal-Adversarial-Prompt

• RUCAIBox / HADES
  [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …
  ☆13Updated 2 weeks ago
• Haochen-Luo / CroPA
  ☆30Updated 4 months ago
• RylanSchaeffer / AstraFellowship-When-Do-VLM-Image-Jailbreaks-Transfer
  Code for Arxiv When Do Universal Image Jailbreaks Transfer Between Vision-Language Models?
  ☆15Updated last month
• YitingQu / unsafe-diffusion
  ☆24Updated 3 months ago
• abc03570128 / Jailbreaking-Attack-against-Multimodal-Large-Language-Model
  ☆37Updated 2 months ago
• erfanshayegani / Jailbreak-In-Pieces
  [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…
  ☆24Updated 5 months ago
• sail-sg / AnyDoor
  AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Models
  ☆43Updated 7 months ago
• thunxxx / MLLM-Jailbreak-evaluation-MMJ-Bench
  ☆18Updated this week
• euanong / image-hijacks
  Official codebase for Image Hijacks: Adversarial Images can Control Generative Models at Runtime
  ☆37Updated last year
• TreeLLi / APT
  One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models
  ☆37Updated 5 months ago
• LiangSiyuan21 / BadCLIP
  ☆15Updated 2 months ago
• ys-zong / VLGuard
  [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.
  ☆44Updated 2 months ago
• jiawangbai / BadCLIP
  Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdf
  ☆17Updated 7 months ago
• cvlab-columbia / ZSRobust4FoundationModel
  ☆38Updated last year
• KuofengGao / Verbose_Images
  [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images
  ☆22Updated 9 months ago
• umd-huang-lab / VLM-Poisoning
  Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"
  ☆27Updated last month
• jiaxiaojunQAQ / I-GCG
  Improved techniques for optimization-based jailbreaking on large language models
  ☆42Updated 5 months ago
• ericyinyzy / VLAttack
  This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2…
  ☆39Updated last week
• BrachioLab / adversarial_prompting
  ☆53Updated last year
• ShawnXYang / C-GSP
  ☆12Updated 2 years ago
• NY1024 / Jailbreak_GPT4o
  ☆16Updated 5 months ago
• Zoky-2020 / SGA
  Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models. [ICCV 2023 Oral]
  ☆47Updated last year
• EddyLuo1232 / JailBreakV_28K
  JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and further assess …
  ☆35Updated 3 months ago
• isXinLiu / MM-SafetyBench
  Accepted by ECCV 2024
  ☆71Updated 3 weeks ago
• inspire-group / tta_risk
  ☆9Updated last year
• UCSC-VLAA / vllm-safety-benchmark
  [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"
  ☆66Updated 11 months ago
• OPTML-Group / QF-Attack
  [CVPR23W] "A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion" by Haomin Zhuang, Yihua Zhang and Sijia Liu
  ☆22Updated 2 months ago
• researchcode001 / Divide-and-Conquer-Attack
  Divide-and-Conquer Attack: Harnessing the Power of LLM to Bypass the Censorship of Text-to-Image Generation Mode
  ☆15Updated 2 months ago
• VITA-Group / Shake-to-Leak
  ☆13Updated 4 months ago
• bboylyg / RNP
  Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)
  ☆28Updated 10 months ago