roywang021 / UMKLinks
Code for ACM MM2024 paper: White-box Multimodal Jailbreaks Against Large Vision-Language Models
☆31Updated last year
Alternatives and similar repositories for UMK
Users that are interested in UMK are comparing it to the libraries listed below
Sorting:
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆34Updated last year
- ☆55Updated last year
- ☆71Updated 7 months ago
- ☆56Updated last year
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆77Updated last year
- ☆54Updated last year
- ☆67Updated 9 months ago
- Accept by CVPR 2025 (highlight)☆22Updated 7 months ago
- This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2…☆64Updated 9 months ago
- ☆37Updated 7 months ago
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆185Updated 6 months ago
- Code for NeurIPS 2024 Paper "Fight Back Against Jailbreaking via Prompt Adversarial Tuning"☆22Updated 8 months ago
- Code for ICCV2025 paper——IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves☆14Updated 5 months ago
- A package that achieves 95%+ transfer attack success rate against GPT-4☆25Updated last year
- ☆108Updated last year
- Code repository for the paper "Heuristic Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models"☆14Updated 5 months ago
- Code for the paper "Jailbreak Large Vision-Language Models Through Multi-Modal Linkage"☆25Updated last year
- Official implementation of Visco-Attack (EMNLP 2025 Main). We will progressively release the code and one-click reproduction scripts.☆26Updated 4 months ago
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆84Updated 8 months ago
- Accepted by ECCV 2024☆179Updated last year
- The Oyster series is a set of safety models developed in-house by Alibaba-AAIG, devoted to building a responsible AI ecosystem. | Oyster …☆57Updated 3 months ago
- Official codebase for Image Hijacks: Adversarial Images can Control Generative Models at Runtime☆54Updated 2 years ago
- ☆20Updated 7 months ago
- Code for "When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search" (NeurIPS 2024)☆17Updated last year
- ☆30Updated last year
- Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment (NeurIPS 2025)☆44Updated 2 months ago
- ☆79Updated last year
- A Survey on Jailbreak Attacks and Defenses against Multimodal Generative Models☆297Updated last month
- [CVPR 2025] Official implementation for "Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbre…☆47Updated 6 months ago
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆58Updated 11 months ago