liuxuannan / Awesome-Multimodal-Jailbreak
A Survey on Jailbreak Attacks and Defenses against Multimodal Generative Models
β132Updated 2 weeks ago
Alternatives and similar repositories for Awesome-Multimodal-Jailbreak:
Users that are interested in Awesome-Multimodal-Jailbreak are comparing it to the libraries listed below
- A collection of resources on attacks and defenses targeting text-to-image diffusion modelsβ59Updated 2 months ago
- [ICLR 2024 Spotlight π₯ ] - [ Best Paper Award SoCal NLP 2023 π] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modalβ¦β41Updated 9 months ago
- π up-to-date & curated list of awesome Attacks on Large-Vision-Language-Models papers, methods & resources.β237Updated this week
- List of T2I safety papers, updated daily, welcome to discuss using Discussionsβ57Updated 7 months ago
- β19Updated 6 months ago
- Accepted by ECCV 2024β109Updated 5 months ago
- β25Updated 7 months ago
- β42Updated 7 months ago
- The official implementation of ECCV'24 paper "To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsβ¦β71Updated 2 weeks ago
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Imagesβ30Updated last year
- β31Updated 8 months ago
- This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2β¦β49Updated 4 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking β¦β17Updated 4 months ago
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdfβ19Updated 11 months ago
- Official implementation of NeurIPS'24 paper "Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Modelβ¦β39Updated 4 months ago
- β32Updated 3 months ago
- A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)β134Updated last week
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shiβ¦β52Updated 8 months ago
- β67Updated 7 months ago
- [NeurIPS-2023] Annual Conference on Neural Information Processing Systemsβ186Updated 2 months ago
- Accepted by IJCAI-24 Survey Trackβ196Updated 6 months ago
- β32Updated 9 months ago
- [MM'23 Oral] "Text-to-image diffusion models can be easily backdoored through multimodal data poisoning"β27Updated last week
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Promptsβ121Updated 3 weeks ago
- A package that achieves 95%+ transfer attack success rate against GPT-4β16Updated 4 months ago
- Benchmarking Physical Risk Awareness of Foundation Model-based Embodied AI Agentsβ14Updated 3 months ago
- β19Updated 10 months ago
- β92Updated last year
- Code for ACM MM2024 paper: White-box Multimodal Jailbreaks Against Large Vision-Language Modelsβ23Updated 2 months ago
- β42Updated 2 months ago