SecurePoL: Integration of Watermarking With Proof-of-Learning to Enhance Security Against Spoofing Attacks
Published in IEEE Access, 2025
SecurePoL presents a dual-layer framework that couples immutable Proof-of-Learning logs with three watermarking strategies (feature-based triggers, sparse parameter perturbations, and a non-intrusive auxiliary head), ensuring verification succeeds only when both the training trajectory and watermark are consistent.
Recommended citation: Ural, O. and Yoshigoe, K. (2025). SecurePoL: Integration of Watermarking With Proof-of-Learning to Enhance Security Against Spoofing Attacks. IEEE Access, vol. 13, pp. 213067-213091. DOI: 10.1109/ACCESS.2025.3642198.
Download Paper