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
☆70Updated 4 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:
- A package that achieves 95%+ transfer attack success rate against GPT-4☆23Updated 10 months ago
- [ICLR 2025] Dissecting adversarial robustness of multimodal language model agents☆99Updated 6 months ago
- A Survey on Jailbreak Attacks and Defenses against Multimodal Generative Models☆216Updated 2 weeks ago
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆67Updated last year
- [ICML 2024] Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models☆140Updated 2 months ago
- ☆102Updated last year
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆52Updated 7 months ago
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shi…☆62Updated last year
- A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)☆162Updated 2 months ago
- ☆33Updated 3 months ago
- ☆58Updated 5 months ago
- ☆46Updated 8 months ago
- ☆50Updated last year
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images☆38Updated last year
- [ICML 2025] X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP☆24Updated 2 months ago
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆73Updated 3 months ago
- List of T2I safety papers, updated daily, welcome to discuss using Discussions☆63Updated last year
- To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models☆31Updated 3 months ago
- ☆30Updated 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…☆80Updated 6 months ago
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.☆74Updated 7 months ago
- Official codebase for Image Hijacks: Adversarial Images can Control Generative Models at Runtime☆50Updated last year
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆27Updated 10 months ago
- [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"☆82Updated last year
- [CVPR 2025] Official implementation for "Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbre…☆35Updated last month
- ☆39Updated 4 months ago
- AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Models☆55Updated last year
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆164Updated 2 months ago
- Comprehensive Assessment of Trustworthiness in Multimodal Foundation Models☆22Updated 5 months ago
- [NeurIPS-2023] Annual Conference on Neural Information Processing Systems☆209Updated 8 months ago