透かしの耐久性

Customized Watermarking for Deep Neural Networks via Label Distribution Perturbation

Authors: Tzu-Yun Chien, Chih-Ya Shen | Published: 2022-08-10
カスタマイズ手法
敵対的サンプル
透かしの耐久性

Subsequent embedding in targeted image steganalysis: Theoretical framework and practical applications

Authors: David Megías, Daniel Lerch-Hostalot | Published: 2021-07-29 | Updated: 2022-03-15
アルゴリズム
実験的検証
透かしの耐久性

Defending against adversarial attacks by randomized diversification

Authors: Olga Taran, Shideh Rezaeifar, Taras Holotyak, Slava Voloshynovskiy | Published: 2019-04-01
敵対的サンプルの検知
敵対的攻撃検出
透かしの耐久性