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...
Na minha lista:
| Principais autores: | , , , , |
|---|---|
| 格式: | Artigo |
| 语言: | Inglês |
| 出版: |
Springer
2026-08-01
|
| 丛编: | Journal of King Saud University: Computer and Information Sciences |
| 主题: | |
| 在线阅读: | https://doi.org/10.1007/s44443-026-01195-3 |
| 标签: |
没有标签, 成为第一个标记此记录!
|