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

Computer Science > Cryptography and Security [Submitted on 10 Jun 2026] T2S: A Rehearsal-Based Approach for Extraction-Resistant Model Watermarking Jian-Ping Mei, Weibin Zhang, Ao Yao, Tiantian Zhu, Jie Xiao 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. Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) Cite as: arXiv:2606.11698 [cs.CR]   (or arXiv:2606.11698v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2606.11698 Focus to learn more Journal reference: ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 2026, pp. 13967-13971 Related DOI: https://doi.org/10.1109/ICASSP55912.2026.11463710 Focus to learn more Submission history From: Weibin Zhang [view email] [v1] Wed, 10 Jun 2026 06:22:40 UTC (649 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)