Work

FedReverse: Multiparty Reversible Deep Neural Network Watermarking

Year: 2024

Type: conference-paper

Abstract: The rising complexity and cost of training DNN models underscore the need for intellectual property protection. In this regard, DNN watermarking has emerged as a crucial safeguarding technique. This paper introduces FedReverse, a multiparty reversible watermarking method that ensures robust copyright protection and minimal performance impact. FedReverse is reversible, allowing collaborative watermark embedding post-training and enables complete removal with unanimous consent. It is resistant to Known Original Attacks (KOA), making watermark forgery and key inference difficult. Comprehensive simulations with MLP and CNN models on varying parameters show FedReverse’s robustness, reversibility, and minimal accuracy impact.

Source: IEEE International Conference on High Performance Computing and Communications (HPCC)

DOI: 10.1109/hpcc64274.2024.00213

Authors: Junlong Mao, Huiyi Tang, Yi Zhang, Fengxia Liu, Hongliang He, Shanxiang Lyu

Institutions: Jinan University, Great Bay University, China University of Geosciences

Language: English

Topic: Advanced Steganography and Watermarking Techniques

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: National Natural Science Foundation of China

OpenAlex ID: W4412610794

FWCI: 0.211

Cites: 34

Cited by: 1

Related to: 10