paper-with-me

Papers

Embedding Watermarks in Diffusion Process for Model Intellectual Property Protection

2024-10-29 · Jijia Yang, Sen Peng, Xiaohua Jia

In practical application, the widespread deployment of diffusion models often necessitates substantial investment in training. As diffusion models find increasingly diverse applications, concerns about potential misuse highlight the imperative for robust intellectual property protection. Current protection strategies either employ backdoor-based methods, integrating a watermark task as a simpler training objective with the main model task, or embedding watermarks directly into the final output samples. However, the former approach is fragile compared to existing backdoor defense techniques, while the latter fundamentally alters the expected output. In this work, we introduce a novel watermarking framework by embedding the watermark into the whole diffusion process, and theoretically ensure that our final output samples contain no additional information. Furthermore, we utilize statistical algorithms to verify the watermark from internally generated model samples without necessitating triggers as conditions. Detailed theoretical analysis and experimental validation demonstrate the effectiveness of our proposed method.

📄 PDF Abstract BibTeX arXiv:2410.22445

Code (0)

등록된 구현이 없습니다.

Tasks

backdoor defense

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Intellectual Property Protection of Diffusion Models via the Watermark Diffusion Process

2023-06-06 · Sen Peng, Yufei Chen, Cong Wang, Xiaohua Jia

Diffusion models have rapidly become a vital part of deep generative architectures, given today's increasing demands. Obtaining large, high-performance diffusion models demands significant resources, highlighting their i…

WET: Overcoming Paraphrasing Vulnerabilities in Embeddings-as-a-Service with Linear Transformation Watermarks

2024-08-29 · Anudeex Shetty, Qiongkai Xu, Jey Han Lau

Embeddings-as-a-Service (EaaS) is a service offered by large language model (LLM) developers to supply embeddings generated by LLMs. Previous research suggests that EaaS is prone to imitation attacks -- attacks that clon…

Language ModelingLanguage ModellingLarge Language Model

Robust Client-Server Watermarking for Split Federated Learning

2025-11-17 · Jiaxiong Tang, Zhengchunmin Dai, Liantao Wu, Peng Sun 외 arxiv

Split Federated Learning (SFL) is renowned for its privacy-preserving nature and low computational overhead among decentralized machine learning paradigms. In this framework, clients employ lightweight models to process …

Federated Learning

SoK: Are Watermarks in LLMs Ready for Deployment?

2025-06-05 · Kieu Dang, Phung Lai, NhatHai Phan, Yelong Shen 외

Large Language Models (LLMs) have transformed natural language processing, demonstrating impressive capabilities across diverse tasks. However, deploying these models introduces critical risks related to intellectual pro…

On the Coexistence and Ensembling of Watermarks

2025-01-29 · Aleksandar Petrov, Shruti Agarwal, Philip H. S. Torr, Adel Bibi 외

Watermarking, the practice of embedding imperceptible information into media such as images, videos, audio, and text, is essential for intellectual property protection, content provenance and attribution. The growing com…