PoLO: Proof-of-Learning and Proof-of-Ownership at Once with Chained Watermarking
classification
💻 cs.CR
cs.AIcs.LG
keywords
textbfpoloaccuracydetectionproofverificationachievesattacks
read the original abstract
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.
This paper has not been read by Pith yet.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.