XuandongZhao / Ginsew
[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
- ☆20Updated last year
- Code for paper: "PromptCARE: Prompt Copyright Protection by Watermark Injection and Verification", IEEE S&P 2024.☆32Updated 8 months ago
- [CVPR 2023] Backdoor Defense via Adaptively Splitting Poisoned Dataset☆49Updated last year
- ☆19Updated last year
- Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation (NeurIPS 2022)☆33Updated 2 years ago
- Code Repo for the NeurIPS 2023 paper "VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models"☆23Updated 7 months ago
- Robust natural language watermarking using invariant features☆25Updated last year
- Backdoor Safety Tuning (NeurIPS 2023 & 2024 Spotlight)☆25Updated 5 months ago
- official implementation of Towards Robust Model Watermark via Reducing Parametric Vulnerability☆14Updated 10 months ago
- Code for the paper "Autoregressive Perturbations for Data Poisoning" (NeurIPS 2022)☆20Updated 7 months ago
- [CCS'22] SSLGuard: A Watermarking Scheme for Self-supervised Learning Pre-trained Encoders☆19Updated 2 years ago
- Source code of paper "An Unforgeable Publicly Verifiable Watermark for Large Language Models" accepted by ICLR 2024☆33Updated 11 months ago
- ☆12Updated 3 years ago
- [BMVC 2023] Backdoor Attack on Hash-based Image Retrieval via Clean-label Data Poisoning☆15Updated last year
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdf☆20Updated last year
- All code and data necessary to replicate experiments in the paper BAGM: A Backdoor Attack for Manipulating Text-to-Image Generative Model…☆11Updated 7 months ago
- Code for paper: PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models, IEEE ICASSP 2024. Demo//124.220.228.133:11107☆17Updated 8 months ago
- PyTorch implementation of our ICLR 2023 paper titled "Is Adversarial Training Really a Silver Bullet for Mitigating Data Poisoning?".☆12Updated 2 years ago
- ☆29Updated 10 months ago
- This code is the official implementation of WEvade.☆38Updated last year
- ☆11Updated 2 years ago
- [MM'23 Oral] "Text-to-image diffusion models can be easily backdoored through multimodal data poisoning"☆28Updated last month
- Github repo for One-shot Neural Backdoor Erasing via Adversarial Weight Masking (NeurIPS 2022)☆15Updated 2 years ago
- Repository for Towards Codable Watermarking for Large Language Models☆36Updated last year
- ☆18Updated last year
- ☆31Updated 3 years ago
- Code for "Adversarial Illusions in Multi-Modal Embeddings"☆20Updated 8 months ago
- [ICLR'21] Dataset Inference for Ownership Resolution in Machine Learning☆32Updated 2 years ago
- [CVPR23W] "A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion" by Haomin Zhuang, Yihua Zhang and Sijia Liu☆26Updated 8 months ago
- CVPR 2025 - Anyattack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models☆18Updated last month