huanranchen / VLMTransfer
A package that achieves 95%+ transfer attack success rate against GPT-4
β14Updated 3 weeks ago
Related projects β
Alternatives and complementary repositories for VLMTransfer
- β30Updated 5 months ago
- [ICLR 2024 Spotlight π₯ ] - [ Best Paper Award SoCal NLP 2023 π] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modalβ¦β26Updated 5 months ago
- [NeurIPS-2023] Annual Conference on Neural Information Processing Systemsβ161Updated last year
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Imagesβ24Updated 9 months ago
- β17Updated last week
- β20Updated last week
- A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)β108Updated 2 weeks ago
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdfβ17Updated 7 months ago
- β23Updated 5 months ago
- Accepted by ECCV 2024β74Updated last month
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"β28Updated last month
- β16Updated 2 months ago
- This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2β¦β40Updated 2 weeks ago
- β25Updated 4 months ago
- A collection of resources on attacks and defenses targeting text-to-image diffusion modelsβ46Updated last week
- One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Modelsβ37Updated this week
- Code for Arxiv When Do Universal Image Jailbreaks Transfer Between Vision-Language Models?β15Updated 2 months ago
- A list of research towards security&privacy in AI-Generated Contentβ12Updated 6 months ago
- β86Updated 9 months ago
- official PyTorch implement of Towards Adversarial Attack on Vision-Language Pre-training Modelsβ49Updated last year
- [ECCV-2024] Transferable Targeted Adversarial Attack, CLIP models, Generative adversarial network, Multi-target attacksβ22Updated 3 months ago
- Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models. [ICCV 2023 Oral]β47Updated last year
- β20Updated 4 months ago
- The official implementation of ECCV'24 paper "To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsβ¦β58Updated 2 weeks ago
- β37Updated 3 months ago
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shiβ¦β45Updated 4 months ago
- [CVPR23W] "A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion" by Haomin Zhuang, Yihua Zhang and Sijia Liuβ24Updated 2 months ago
- β56Updated 3 months ago
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794β¦β12Updated 3 months ago
- The official code of the paper "Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate".β80Updated 3 weeks ago