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...
保存先:
| 主要な著者: | , |
|---|---|
| フォーマット: | Artigo |
| 言語: | Inglês |
| 出版事項: |
IEEE
2025-01-01
|
| シリーズ: | IEEE Access |
| 主題: | |
| オンライン･アクセス: | https://ieeexplore.ieee.org/document/11293969/ |
| タグ: |
タグなし, このレコードへの初めてのタグを付けませんか!
|