FedReverse: Multiparty Reversible Deep Neural Network Watermarking

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.