Beyond A Fixed Seal: Adaptive Stealing Watermark in Large Language Models

Computer Science > Cryptography and Security [Submitted on 13 Apr 2026] Beyond A Fixed Seal: Adaptive Stealing Watermark in Large Language Models Shuhao Zhang, Yuli Chen, Jiale Han, Bo Cheng, Jiabao Ma Watermarking provides a critical safeguard for large language model (LLM) services by facilitating the detection of LLM-generated text. Correspondingly, stealing watermark algorithms (SWAs) derive watermark information from watermarked texts generated by victim LLMs to craft highly targeted adversarial attacks, which compromise the reliability of watermarks. Existing SWAs rely on fixed strategies, overlooking the non-uniform distribution of stolen watermark information and the dynamic nature of real-world LLM generation processes. To address these limitations, we propose Adaptive Stealing (AS), a novel SWA featuring enhanced design flexibility through Position-Based Seal Construction and Adaptive Selection modules. AS operates by defining multiple attack perspectives derived from distinct activation states of contextually ordered tokens. During attack execution, AS dynamically selects the optimal perspective based on watermark compatibility, generation priority, and dynamic generation relevance. Our experiments demonstrate that AS significantly increases steal efficiency against target watermarks under identical experimental conditions. These findings highlight the need for more robust LLM watermarks to withstand potential attacks. We release our code to the community for future research\footnote{this https URL}. Comments: 18 pages,6 figures Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) Cite as: arXiv:2604.10893 [cs.CR]   (or arXiv:2604.10893v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2604.10893 Focus to learn more Submission history From: Shuhao Zhang [view email] [v1] Mon, 13 Apr 2026 01:46:51 UTC (1,600 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-04 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?)