Rethinking White-Box Watermarks on Deep Learning Models under Neural Structural Obfuscation
This exposes a critical security flaw in copyright protection for AI corporations, highlighting an incremental but important vulnerability in existing watermarking methods.
The paper tackles the vulnerability of white-box DNN watermarks to neural structural obfuscation using dummy neurons, showing that nine published watermarking schemes require amendments to their verification procedures.
Copyright protection for deep neural networks (DNNs) is an urgent need for AI corporations. To trace illegally distributed model copies, DNN watermarking is an emerging technique for embedding and verifying secret identity messages in the prediction behaviors or the model internals. Sacrificing less functionality and involving more knowledge about the target DNN, the latter branch called \textit{white-box DNN watermarking} is believed to be accurate, credible and secure against most known watermark removal attacks, with emerging research efforts in both the academy and the industry. In this paper, we present the first systematic study on how the mainstream white-box DNN watermarks are commonly vulnerable to neural structural obfuscation with \textit{dummy neurons}, a group of neurons which can be added to a target model but leave the model behavior invariant. Devising a comprehensive framework to automatically generate and inject dummy neurons with high stealthiness, our novel attack intensively modifies the architecture of the target model to inhibit the success of watermark verification. With extensive evaluation, our work for the first time shows that nine published watermarking schemes require amendments to their verification procedures.