Backdoor-free model watermarking via differential verification of adversarial samples and multi-bit information extraction
Abstract Model watermarking is a commonly used ownership verification technique for protecting the copyright of deep learning models. However, in practically deployed black-box model service scenarios, existing methods typically rely on misclassification-based backdoor trigger mechanisms, or assume...
Guardat en:
| Autors principals: | , , , , |
|---|---|
| Format: | Artigo |
| Idioma: | Inglês |
| Publicat: |
Springer
2026-08-01
|
| Col·lecció: | Journal of King Saud University: Computer and Information Sciences |
| Matèries: | |
| Accés en línia: | https://doi.org/10.1007/s44443-026-01195-3 |
| Etiquetes: |
Sense etiquetes, Sigues el primer a etiquetar aquest registre!
|