DeepEclipse: How to Break White-Box DNN-Watermarking Schemes
This addresses the challenge of IP infringement for DNN owners by exposing vulnerabilities in existing watermarking schemes, though it is incremental in the competitive field of watermarking and removal.
The paper tackles the problem of protecting intellectual property in deep neural networks by proposing DeepEclipse, a framework that removes white-box watermarks without prior knowledge of the scheme or additional data, reducing detection to random guessing while maintaining model accuracy.
Deep Learning (DL) models have become crucial in digital transformation, thus raising concerns about their intellectual property rights. Different watermarking techniques have been developed to protect Deep Neural Networks (DNNs) from IP infringement, creating a competitive field for DNN watermarking and removal methods. The predominant watermarking schemes use white-box techniques, which involve modifying weights by adding a unique signature to specific DNN layers. On the other hand, existing attacks on white-box watermarking usually require knowledge of the specific deployed watermarking scheme or access to the underlying data for further training and fine-tuning. We propose DeepEclipse, a novel and unified framework designed to remove white-box watermarks. We present obfuscation techniques that significantly differ from the existing white-box watermarking removal schemes. DeepEclipse can evade watermark detection without prior knowledge of the underlying watermarking scheme, additional data, or training and fine-tuning. Our evaluation reveals that DeepEclipse excels in breaking multiple white-box watermarking schemes, reducing watermark detection to random guessing while maintaining a similar model accuracy as the original one. Our framework showcases a promising solution to address the ongoing DNN watermark protection and removal challenges.