erfanshayegani / Jailbreak-In-Pieces

Related projects: ⓘ

• abc03570128 / Jailbreaking-Attack-against-Multimodal-Large-Language-Model
  ☆30Updated last month
• umd-huang-lab / VLM-Poisoning
  Code for the paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"
  ☆21Updated 5 months ago
• KuofengGao / Verbose_Images
  [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images
  ☆17Updated 7 months ago
• NY1024 / BAP-Jailbreak-Vision-Language-Models-via-Bi-Modal-Adversarial-Prompt
  ☆13Updated 3 months ago
• isXinLiu / MM-SafetyBench
  Accepted by ECCV 2024
  ☆59Updated 2 months ago
• SaFoLab-WISC / AdaShield
  [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shi…
  ☆34Updated 2 months ago
• YitingQu / unsafe-diffusion
  ☆22Updated 2 months ago
• Haochen-Luo / CroPA
  ☆24Updated 3 months ago
• VITA-Group / Shake-to-Leak
  ☆14Updated 2 months ago
• EddyLuo1232 / JailBreakV_28K
  JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and further assess …
  ☆29Updated 2 months ago
• ericyinyzy / VLAttack
  This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2…
  ☆29Updated 8 months ago
• TreeLLi / APT
  One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models
  ☆31Updated 4 months ago
• 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"
  ☆61Updated 9 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
  ☆21Updated 3 weeks ago
• cvlab-columbia / ZSRobust4FoundationModel
  ☆35Updated last year
• OPTML-Group / Diffusion-MU-Attack
  The official implementation of ECCV'24 paper "To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Uns…
  ☆43Updated last month
• yunqing-me / AttackVLM
  [NeurIPS-2023] Annual Conference on Neural Information Processing Systems
  ☆147Updated 10 months ago
• ffhibnese / CGNC_Targeted_Adversarial_Attacks
  [ECCV-2024] Transferable Targeted Adversarial Attack, CLIP models, Generative adversarial network, Multi-target attacks
  ☆18Updated last month
• ys-zong / VLGuard
  [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.
  ☆36Updated 3 weeks ago
• sail-sg / AnyDoor
  AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Models
  ☆39Updated 5 months ago
• thu-ml / Attack-Bard
  ☆84Updated 7 months ago
• ZhentingWang / DIAGNOSIS
  ☆14Updated 4 months ago
• jiaxiaojunQAQ / I-GCG
  Improved techniques for optimization-based jailbreaking on large language models
  ☆33Updated 3 months ago
• liuyixin-louis / MetaCloak
  [CVPR'24 Oral] Metacloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learning
  ☆18Updated 2 months ago
• jiawangbai / BadCLIP
  Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdf
  ☆14Updated 5 months ago
• zhaisf / BadT2I
  [MM'23 Oral] "Text-to-image diffusion models can be easily backdoored through multimodal data poisoning"
  ☆19Updated last week
• Zoky-2020 / SGA
  Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models. [ICCV 2023 Oral]
  ☆45Updated last year
• nishadsinghi / CleanCLIP
  Official PyTorch implementation of "CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning" @ ICCV 2023
  ☆27Updated 8 months ago
• chenchenygu / watermark-learnability
  ☆18Updated 3 months ago
• KuofengGao / ASD
  [CVPR 2023] Backdoor Defense via Adaptively Splitting Poisoned Dataset
  ☆40Updated 5 months ago