ffhibnese / CPGC_VLP_Universal_Attacks
Universal Adversarial Attack, Multimodal Adversarial Attacks, VLP models, Contrastive Learning, Cross-modal Perturbation Generator, Generative Attacks.
☆16Updated 5 months ago
Alternatives and similar repositories for CPGC_VLP_Universal_Attacks:
Users that are interested in CPGC_VLP_Universal_Attacks are comparing it to the libraries listed below
- ☆21Updated 7 months ago
- Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models. [ICCV 2023 Oral]☆59Updated last year
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdf☆20Updated last year
- [ECCV-2024] Transferable Targeted Adversarial Attack, CLIP models, Generative adversarial network, Multi-target attacks☆32Updated 8 months ago
- [ECCV2024] Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajector…☆24Updated 4 months ago
- This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2…☆50Updated 3 weeks ago
- [CVPR23W] "A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion" by Haomin Zhuang, Yihua Zhang and Sijia Liu☆26Updated 7 months ago
- ☆69Updated 8 months ago
- ☆39Updated 10 months ago
- ☆31Updated 9 months ago
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆47Updated 10 months ago
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images☆33Updated last year
- A collection of resources on attacks and defenses targeting text-to-image diffusion models☆63Updated 3 weeks ago
- ☆27Updated 8 months ago
- ☆25Updated this week
- One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models☆47Updated 3 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆28Updated 5 months ago
- A package that achieves 95%+ transfer attack success rate against GPT-4☆17Updated 5 months ago
- [CVPR 2024] Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transfomers☆17Updated 5 months ago
- AdvDiffuser: Natural Adversarial Example Synthesis with Diffusion Models (ICCV 2023)☆18Updated last year
- ☆42Updated 4 months ago
- official PyTorch implement of Towards Adversarial Attack on Vision-Language Pre-training Models☆59Updated 2 years ago
- ☆44Updated 8 months ago
- Pytorch implementation for the pilot study on the robustness of latent diffusion models.☆10Updated last year
- ☆9Updated 7 months ago
- [BMVC 2023] Backdoor Attack on Hash-based Image Retrieval via Clean-label Data Poisoning☆15Updated last year
- [MM'23 Oral] "Text-to-image diffusion models can be easily backdoored through multimodal data poisoning"☆28Updated last month
- Code repository for CVPR2024 paper 《Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness》☆20Updated 10 months ago
- [CVPR 2023] Backdoor Defense via Adaptively Splitting Poisoned Dataset☆48Updated last year
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆19Updated 5 months ago