VILA-Lab / M-Attack
A Simple Baseline Achieving Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1. Paper at: https://arxiv.org/abs/2503.10635
☆46Updated last week
Alternatives and similar repositories for M-Attack:
Users that are interested in M-Attack are comparing it to the libraries listed below
- [ICML 2024] Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models☆123Updated 4 months ago
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.☆61Updated 2 months ago
- [ArXiv 2024] Denial-of-Service Poisoning Attacks on Large Language Models☆17Updated 5 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆27Updated 5 months ago
- The official code of the paper "Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate".☆96Updated 4 months ago
- AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Models☆51Updated 11 months ago
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shi…☆54Updated 8 months ago
- A package that achieves 95%+ transfer attack success rate against GPT-4☆17Updated 5 months ago
- ☆32Updated 3 months ago
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆45Updated 9 months ago
- [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"☆78Updated last year
- [ICLR 2025] Dissecting Adversarial Robustness of Multimodal LM Agents☆77Updated last month
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆44Updated 2 months ago
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images☆32Updated last year
- ECSO (Make MLLM safe without neither training nor any external models!) (https://arxiv.org/abs/2403.09572)☆23Updated 4 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆18Updated 5 months ago
- ☆36Updated 9 months ago
- ☆27Updated last year
- The official repository for paper "MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance"☆35Updated 11 months ago
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆127Updated last month
- ☆40Updated 3 months ago
- The official implementation of ECCV'24 paper "To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Uns…☆72Updated last month
- ☆93Updated last year
- [NeurIPS-2023] Annual Conference on Neural Information Processing Systems☆186Updated 3 months ago
- Improving Your Model Ranking on Chatbot Arena by Vote Rigging☆19Updated last month
- Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"☆28Updated last month
- [ICML 2024 Oral] Official code repository for MLLM-as-a-Judge.☆65Updated last month
- Official codebase for Image Hijacks: Adversarial Images can Control Generative Models at Runtime☆44Updated last year
- One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models☆47Updated 3 months ago
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆51Updated 8 months ago