This repo include papers about the watermark method for large language model and normal language model. Continuously updated
-
Watermarking Pre-trained Language Models with Backdooring
-
(AAAI-2023) PLMmark: A Secure and Robust Black-Box Watermarking Framework for Pre-trained Language Models
-
(AAAI2022) Protecting Intellectual Property of Language Generation APIs with Lexical Watermark Code
-
(ACL2023) Robust Multi-bit Natural Language Watermarking through Invariant Features Code
-
Distillation-Resistant Watermarking for Model Protection in NLP Code
-
(ICML 2023) A Watermark for Large Language Models Code
-
(Neurips 2022) CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks Code
-
(ACL2023) Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark Code
-
Robust Distortion-free Watermarks for Language Models Code
- (ICCV 2023) The Stable Signature: Rooting Watermarks in Latent Diffusion Models Code
- (ACM Multimedia 2023) DocDiff: Document Enhancement via Residual Diffusion Models Code
- (MM 2022) Towards Blind Watermarking: Combining Invertible and Non-invertible Mechanisms Code
- (USENIX 2023) Glaze: Protecting artists from style mimicry by text-to-image models Code
- (ACM MM 2023) Flexible and Secure Watermarking for Latent Diffusion Model
- (CVPR Workshops 2023)RoSteALS: Robust Steganography using Autoencoder Latent Space Code
- (~ 2023) Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust Code
- (~ 2023) Invisible Image Watermarks Are Provably Removable Using Generative AI Code
- (~ 2023) A Recipe for Watermarking Diffusion Models Code
- (~ 2023) On Evaluating Adversarial Robustness of Large Vision-Language Models Code
- (~ 2023) Watermarking Diffusion Model
- (~ 2023) Protecting the Intellectual Property of Diffusion Models by the Watermark Diffusion Process
- (~ 2023) DiffusionShield: A Watermark for Copyright Protection against Generative Diffusion Models
- (~ 2023) Catch You Everything Everywhere: Guarding Textual Inversion via Concept Watermarking
- (~ 2023) Towards the Vulnerability of Watermarking Artificial Intelligence Generated Content
- (~ 2032) Hey That's Mine Imperceptible Watermarks are Preserved in Diffusion Generated Outputs