SecurePoL: Integration of Watermarking With Proof-of-Learning to Enhance Security Against Spoofing Attacks
Proof-of-Learning (PoL) attests training effort but remains vulnerable to tolerance-based spoofing, while model watermarking (WM) protects ownership without verifying how a model was trained. We present SecurePoL, a dual-layer framework that couples immutable PoL logs with three watermarking strateg...
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Artigo |
| Lingua: | Inglês |
| Pubblicazione: |
IEEE
2025-01-01
|
| Serie: | IEEE Access |
| Soggetti: | |
| Accesso online: | https://ieeexplore.ieee.org/document/11293969/ |
| Tags: |
Nessun Tag, puoi essere il primo ad aggiungerne!!
|