ClearMark: Intuitive and Robust Model Watermarking via Transposed Model Training
This addresses the need for intuitive and robust ownership verification for model creators, though it is incremental as it builds on existing watermarking methods.
The paper tackles the problem of non-intuitive and fragile deep neural network watermarking for ownership proof by introducing ClearMark, which embeds visible watermarks for human assessment and achieves an 8,544-bit capacity with superior robustness across datasets and architectures.
Due to costly efforts during data acquisition and model training, Deep Neural Networks (DNNs) belong to the intellectual property of the model creator. Hence, unauthorized use, theft, or modification may lead to legal repercussions. Existing DNN watermarking methods for ownership proof are often non-intuitive, embed human-invisible marks, require trust in algorithmic assessment that lacks human-understandable attributes, and rely on rigid thresholds, making it susceptible to failure in cases of partial watermark erasure. This paper introduces ClearMark, the first DNN watermarking method designed for intuitive human assessment. ClearMark embeds visible watermarks, enabling human decision-making without rigid value thresholds while allowing technology-assisted evaluations. ClearMark defines a transposed model architecture allowing to use of the model in a backward fashion to interwove the watermark with the main task within all model parameters. Compared to existing watermarking methods, ClearMark produces visual watermarks that are easy for humans to understand without requiring complex verification algorithms or strict thresholds. The watermark is embedded within all model parameters and entangled with the main task, exhibiting superior robustness. It shows an 8,544-bit watermark capacity comparable to the strongest existing work. Crucially, ClearMark's effectiveness is model and dataset-agnostic, and resilient against adversarial model manipulations, as demonstrated in a comprehensive study performed with four datasets and seven architectures.