透かし設計

Featurized Bidirectional GAN: Adversarial Defense via Adversarially Learned Semantic Inference

Authors: Ruying Bao, Sihang Liang, Qingcan Wang | Published: 2018-05-21 | Updated: 2018-09-29
モデルの頑健性保証
敵対的攻撃検出
透かし設計

Adversarial Frontier Stitching for Remote Neural Network Watermarking

Authors: Erwan Le Merrer, Patrick Perez, Gilles Trédan | Published: 2017-11-06 | Updated: 2019-08-07
敵対的サンプル
敵対的学習
透かし設計