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
☆62Updated last month
Alternatives and similar repositories for M-Attack
Users that are interested in M-Attack are comparing it to the libraries listed below
Sorting:
- [ICLR 2025] Dissecting adversarial robustness of multimodal language model agents☆88Updated 3 months ago
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.☆71Updated 4 months ago
- ☆34Updated 2 months ago
- [ArXiv 2024] Denial-of-Service Poisoning Attacks on Large Language Models☆18Updated 7 months ago
- [ICML 2024] Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models☆130Updated 6 months ago
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images☆35Updated last year
- ☆46Updated 2 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆61Updated 4 months ago
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆49Updated 4 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆19Updated 7 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆28Updated 7 months ago
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆141Updated 3 months ago
- Awesome Jailbreak, red teaming arxiv papers (Automatically Update Every 12th hours)☆38Updated this week
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shi…☆58Updated 10 months ago
- A package that achieves 95%+ transfer attack success rate against GPT-4☆20Updated 7 months ago
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆56Updated last year
- ☆27Updated 7 months ago
- To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models☆30Updated 2 weeks ago
- [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"☆80Updated last year
- ☆98Updated last year
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆63Updated 3 weeks ago
- A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)☆145Updated 2 months ago
- Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"☆37Updated 3 months ago
- ECSO (Make MLLM safe without neither training nor any external models!) (https://arxiv.org/abs/2403.09572)☆23Updated 7 months ago
- [CVPR 2025] Official implementation for "Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbre…☆20Updated last week
- ☆42Updated last year
- The official repository for paper "MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance"☆37Updated last year
- The official code of the paper "Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate".☆98Updated 6 months ago
- Accepted by ECCV 2024☆130Updated 7 months ago
- ☆43Updated 6 months ago