XuandongZhao / GinsewLinks
[ICML 2023] Protecting Language Generation Models via Invisible Watermarking
☆13Updated last year
Alternatives and similar repositories for Ginsew
Users that are interested in Ginsew are comparing it to the libraries listed below
Sorting:
- ☆10Updated 5 months ago
- ☆20Updated last year
- Code Repo for the NeurIPS 2023 paper "VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models"☆23Updated last month
- [CVPR 2023] Backdoor Defense via Adaptively Splitting Poisoned Dataset☆49Updated last year
- ☆20Updated last year
- [CVPR23W] "A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion" by Haomin Zhuang, Yihua Zhang and Sijia Liu☆26Updated 9 months ago
- All code and data necessary to replicate experiments in the paper BAGM: A Backdoor Attack for Manipulating Text-to-Image Generative Model…☆11Updated 8 months ago
- Code for paper: "PromptCARE: Prompt Copyright Protection by Watermark Injection and Verification", IEEE S&P 2024.☆32Updated 9 months ago
- [AAAI 2024] Data-Free Hard-Label Robustness Stealing Attack☆13Updated last year
- Code for paper: PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models, IEEE ICASSP 2024. Demo//124.220.228.133:11107☆17Updated 9 months ago
- ☆16Updated 2 years ago
- [MM'23 Oral] "Text-to-image diffusion models can be easily backdoored through multimodal data poisoning"☆28Updated 3 months ago
- ☆34Updated 10 months ago
- Code for the paper "Autoregressive Perturbations for Data Poisoning" (NeurIPS 2022)☆20Updated 8 months ago
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdf☆20Updated last year
- Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation (NeurIPS 2022)☆33Updated 2 years ago
- Divide-and-Conquer Attack: Harnessing the Power of LLM to Bypass the Censorship of Text-to-Image Generation Mode☆18Updated 3 months ago
- ☆18Updated last year
- This code is the official implementation of WEvade.☆39Updated last year
- Backdoor Safety Tuning (NeurIPS 2023 & 2024 Spotlight)☆26Updated 6 months ago
- [CCS'22] SSLGuard: A Watermarking Scheme for Self-supervised Learning Pre-trained Encoders☆20Updated 2 years ago
- ☆44Updated last year
- CVPR 2025 - Anyattack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models☆30Updated 3 months ago
- ☆35Updated 2 years ago
- ☆20Updated 6 months ago
- Code of paper [CVPR'24: Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?]☆17Updated last year
- ☆57Updated last year
- ☆29Updated last year
- ☆26Updated 10 months ago
- ☆53Updated 2 years ago