XuandongZhao / Ginsew
[ICML 2023] Protecting Language Generation Models via Invisible Watermarking
☆13Updated last year
Related projects ⓘ
Alternatives and complementary repositories for Ginsew
- ☆16Updated 6 months ago
- Code for paper: "PromptCARE: Prompt Copyright Protection by Watermark Injection and Verification", IEEE S&P 2024.☆28Updated 3 months ago
- [MM'23 Oral] "Text-to-image diffusion models can be easily backdoored through multimodal data poisoning"☆22Updated last month
- [CVPR 2023] Backdoor Defense via Adaptively Splitting Poisoned Dataset☆44Updated 7 months ago
- ICCV 2021, We find most existing triggers of backdoor attacks in deep learning contain severe artifacts in the frequency domain. This Rep…☆40Updated 2 years ago
- ☆16Updated last year
- Robust natural language watermarking using invariant features☆25Updated last year
- [ICLR'21] Dataset Inference for Ownership Resolution in Machine Learning☆31Updated 2 years ago
- Source code of paper "An Unforgeable Publicly Verifiable Watermark for Large Language Models" accepted by ICLR 2024☆27Updated 5 months ago
- Repository for Towards Codable Watermarking for Large Language Models☆29Updated last year
- ☆17Updated 2 years ago
- ☆20Updated last year
- Official repo to reproduce the paper "How to Backdoor Diffusion Models?" published at CVPR 2023☆82Updated 2 months ago
- Code Repo for the NeurIPS 2023 paper "VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models"☆17Updated 2 months ago
- This is the official implementation of our paper 'Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protecti…☆51Updated 7 months ago
- ☆21Updated 5 months ago
- ☆19Updated 3 months ago
- Code for paper: PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models, IEEE ICASSP 2024. Demo//124.220.228.133:11107☆12Updated 3 months ago
- Code for the paper "Autoregressive Perturbations for Data Poisoning" (NeurIPS 2022)☆18Updated 2 months ago
- Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation (NeurIPS 2022)☆33Updated last year
- Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)☆28Updated 10 months ago
- official implementation of Towards Robust Model Watermark via Reducing Parametric Vulnerability☆12Updated 5 months ago
- ☆30Updated 2 years ago
- Code for identifying natural backdoors in existing image datasets.☆15Updated 2 years ago
- Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"☆55Updated last year
- Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"☆35Updated 4 months ago
- ☆12Updated 3 years ago
- ☆41Updated last year
- Official Implementation of NIPS 2022 paper Pre-activation Distributions Expose Backdoor Neurons☆14Updated last year
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdf☆17Updated 7 months ago