PoLO: Proof-of-Learning and Proof-of-Ownership at Once with Chained Watermarking

Computer Science > Cryptography and Security [Submitted on 18 May 2025 (v1), last revised 24 Apr 2026 (this version, v2)] PoLO: Proof-of-Learning and Proof-of-Ownership at Once with Chained Watermarking Haiyu Deng, Yanna Jiang, Guangsheng Yu, Qin Wang, Xu Wang, Baihe Ma, Wei Ni, Ren Ping Liu Our evaluation shows that PoLO achieves \textbf{99\%} watermark detection accuracy for ownership verification, while preserving data privacy and cutting verification costs to just \textbf{1.5--10\%} of traditional methods. Forging PoLO demands \textbf{1.1--4\times} more resources than honest proof generation, with the original proof retaining over \textbf{90\%} detection accuracy even after attacks. Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) Cite as: arXiv:2505.12296 [cs.CR]   (or arXiv:2505.12296v2 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2505.12296 Focus to learn more Submission history From: Qin Wang [view email] [v1] Sun, 18 May 2025 08:19:18 UTC (7,668 KB) [v2] Fri, 24 Apr 2026 07:54:43 UTC (5,055 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2025-05 Change to browse by: cs cs.AI cs.LG 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?)