2 papers
cs.CR2026
EmbTracker: Traceable Black-box Watermarking for Federated Language Models
Haodong Zhao, Jinming Hu, Yijie Bai +6
Federated Language Model (FedLM) allows a collaborative learning without sharing raw data, yet it introduces a critical vulnerability, as every untrustworthy client may leak the re…
cs.CR2024
Revisiting the Information Capacity of Neural Network Watermarks: Upper Bound Estimation and Beyond
Fangqi Li, Haodong Zhao, Wei Du +1
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…