KuofengGao / Verbose_Images
[ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images
☆22Updated 9 months ago
Related projects ⓘ
Alternatives and complementary repositories for Verbose_Images
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdf☆17Updated 7 months ago
- ☆15Updated 2 months ago
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆24Updated 5 months ago
- Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models. [ICCV 2023 Oral]☆47Updated last year
- [CVPR 2024] Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transfomers☆15Updated 2 weeks ago
- ☆24Updated 3 months ago
- The official implementation of our CVPR 2023 paper "Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consist…☆19Updated last year
- [CVPR 2023] Backdoor Defense via Adaptively Splitting Poisoned Dataset☆44Updated 7 months ago
- This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2…☆39Updated last week
- ☆30Updated 4 months ago
- Universal Adversarial Attack, Multimodal Adversarial Attacks, VLP models, Contrastive Learning, Cross-modal Perturbation Generator, Gener…☆10Updated 3 weeks ago
- ☆20Updated 5 months ago
- [BMVC 2023] Backdoor Attack on Hash-based Image Retrieval via Clean-label Data Poisoning☆14Updated last year
- ☆16Updated 6 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆13Updated 2 weeks ago
- [ECCV-2024] Transferable Targeted Adversarial Attack, CLIP models, Generative adversarial network, Multi-target attacks☆20Updated 3 months ago
- official PyTorch implement of Towards Adversarial Attack on Vision-Language Pre-training Models☆48Updated last year
- [CVPR23W] "A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion" by Haomin Zhuang, Yihua Zhang and Sijia Liu☆22Updated 2 months ago
- ☆19Updated 3 months ago
- One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models☆37Updated 5 months ago
- The official implementation of ECCV'24 paper "To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Uns…☆57Updated this week
- ☆38Updated last year
- ☆56Updated 3 months ago
- Improved techniques for optimization-based jailbreaking on large language models☆42Updated 5 months ago
- Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation (NeurIPS 2022)☆33Updated last year
- AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Models☆43Updated 7 months ago
- ☆85Updated 8 months ago
- ☆37Updated 2 months ago
- ☆12Updated 2 years ago
- Code for Arxiv When Do Universal Image Jailbreaks Transfer Between Vision-Language Models?☆15Updated last month