Revisiting the Information Capacity of Neural Network Watermarks: Upper Bound Estimation and Beyond

arXiv:2402.12720v1 Announce Type: new
Abstract: To trace the copyright of deep neural networks, an owner can embed its identity information into its model as a watermark. The capacity of the watermark quantify the maximal volume of information that can be verified from the watermarked model. Current studies on capacity focus on the ownership verification accuracy under ordinary removal attacks and fail to capture the relationship between robustness and fidelity. This paper studies the capacity of deep neural network watermarks from …

arxiv beyond can copyright cs.ai cs.cr current identity information network networks neural network neural networks studies trace verified watermarks