T2S: A Rehearsal-Based Approach for Extraction-Resistant Model Watermarking

June 10, 2026 ยท Grace Period ยท ๐Ÿ› ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 2026, pp. 13967-13971

โณ Grace Period
This paper is less than 90 days old. We give authors time to release their code before passing judgment.
Authors Jian-Ping Mei, Weibin Zhang, Ao Yao, Tiantian Zhu, Jie Xiao arXiv ID 2606.11698 Category cs.CR: Cryptography & Security Cross-listed cs.AI Citations 0 Venue ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 2026, pp. 13967-13971
Abstract
Model watermarking safeguards AI model intellectual property by embedding distinctive knowledge that induces unique behavioral signatures. The primary technical challenge lies in ensuring watermark robustness against various post-processing attacks on the watermarked model. Model extraction attacks emerge as the most severe threat, where adversaries exploit prediction outputs to train surrogate models that illegally replicate the original model's functionality. In this work, we propose a rehearsal-based watermark embedding framework to enhance the robustness of model watermarks against model extraction attacks. By simulating the extraction process, our method leverages the loss of a \textit{simulated stolen model} on a trigger set as a training signal to fine-tune the watermark knowledge within the target model. This fine-tuning step encourages the watermark to be embedded in a way that boosts transferability, thereby increasing its chances of persisting and remaining detectable in stolen models. Comprehensive experiments conducted under diverse settings demonstrate that the proposed method significantly improves the robustness of model watermarks against both model extraction and subsequent watermark removal attacks.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Cryptography & Security