Sadcardation / MLLM-RefusalLinks
Repository for the Paper: Refusing Safe Prompts for Multi-modal Large Language Models
☆18Updated last year
Alternatives and similar repositories for MLLM-Refusal
Users that are interested in MLLM-Refusal are comparing it to the libraries listed below
Sorting:
- ☆53Updated last year
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆56Updated 10 months ago
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆74Updated last year
- ☆63Updated 7 months ago
- [CVPR2025] Official Repository for IMMUNE: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment☆25Updated 5 months ago
- A package that achieves 95%+ transfer attack success rate against GPT-4☆23Updated last year
- Code for ICLR 2025 Failures to Find Transferable Image Jailbreaks Between Vision-Language Models☆32Updated 5 months ago
- Comprehensive Assessment of Trustworthiness in Multimodal Foundation Models☆24Updated 8 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆32Updated last year
- ☆49Updated last year
- Code for ICCV2025 paper——IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves☆14Updated 4 months ago
- ☆105Updated last year
- [NeurIPS 2024] Fight Back Against Jailbreaking via Prompt Adversarial Tuning☆10Updated last year
- Official Code for "Baseline Defenses for Adversarial Attacks Against Aligned Language Models"☆28Updated 2 years ago
- [ICML 2025] X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP☆31Updated 4 months ago
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images☆40Updated last year
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆80Updated 6 months ago
- Code for NeurIPS 2024 Paper "Fight Back Against Jailbreaking via Prompt Adversarial Tuning"☆20Updated 6 months ago
- [NeurIPS 2023] Differentially Private Image Classification by Learning Priors from Random Processes☆12Updated 2 years ago
- [ICLR 2025] BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks☆30Updated 2 weeks ago
- [CVPR 2025] Official implementation for JOOD "Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy"☆18Updated 5 months ago
- ☆37Updated 5 months ago
- ☆54Updated 11 months ago
- Accept by CVPR 2025 (highlight)☆21Updated 5 months ago
- Code for the paper "Jailbreak Large Vision-Language Models Through Multi-Modal Linkage"☆22Updated 11 months ago
- [ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization☆29Updated last year
- Official codebase for Image Hijacks: Adversarial Images can Control Generative Models at Runtime☆52Updated 2 years ago
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆22Updated last year
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆178Updated 4 months ago
- The Oyster series is a set of safety models developed in-house by Alibaba-AAIG, devoted to building a responsible AI ecosystem. | Oyster …☆55Updated 2 months ago