VILA-Lab / M-AttackLinks
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
☆63Updated 2 months ago
Alternatives and similar repositories for M-Attack
Users that are interested in M-Attack are comparing it to the libraries listed below
Sorting:
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images☆35Updated last year
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆22Updated 8 months ago
- A package that achieves 95%+ transfer attack success rate against GPT-4☆20Updated 8 months ago
- ☆99Updated last year
- [ICLR 2025] Dissecting adversarial robustness of multimodal language model agents☆91Updated 4 months ago
- [ICML 2024] Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models☆133Updated 3 weeks ago
- ☆34Updated 2 months ago
- ☆47Updated 2 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆29Updated 8 months ago
- ☆46Updated last year
- Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"☆42Updated 4 months ago
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆58Updated last year
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shi…☆59Updated 11 months ago
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆67Updated last month
- [ArXiv 2024] Denial-of-Service Poisoning Attacks on Large Language Models☆19Updated 8 months ago
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.☆73Updated 5 months ago
- [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"☆81Updated last year
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆50Updated 5 months ago
- [CVPR 2025] Official implementation for "Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbre…☆24Updated last month
- ☆22Updated last year
- The official repository for paper "MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance"☆37Updated last year
- A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)☆148Updated 3 months ago
- ☆29Updated last month
- CVPR 2025 - Anyattack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models☆35Updated 3 months ago
- ☆29Updated last week
- Official codebase for Image Hijacks: Adversarial Images can Control Generative Models at Runtime☆47Updated last year
- To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models☆31Updated last month
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆61Updated 5 months ago
- ☆44Updated 6 months ago
- ECSO (Make MLLM safe without neither training nor any external models!) (https://arxiv.org/abs/2403.09572)☆25Updated 7 months ago