How benign is benign overfitting?
Authors: Amartya Sanyal, Puneet K Dokania, Varun Kanade, Philip H. S. Torr | Published: 2020-07-08
敵対的サンプル
Regional Image Perturbation Reduces $L_p$ Norms of Adversarial Examples While Maintaining Model-to-model Transferability
Authors: Utku Ozbulak, Jonathan Peck, Wesley De Neve, Bart Goossens, Yvan Saeys, Arnout Van Messem | Published: 2020-07-07 | Updated: 2020-07-18
Adversarial Machine Learning Attacks and Defense Methods in the Cyber Security Domain
Authors: Ihai Rosenberg, Asaf Shabtai, Yuval Elovici, Lior Rokach | Published: 2020-07-05 | Updated: 2021-03-13
Relationship between manifold smoothness and adversarial vulnerability in deep learning with local errors
Authors: Zijian Jiang, Jianwen Zhou, Haiping Huang | Published: 2020-07-04 | Updated: 2020-12-23
Deep Learning Defenses Against Adversarial Examples for Dynamic Risk Assessment
Authors: Xabier Echeberria-Barrio, Amaia Gil-Lerchundi, Ines Goicoechea-Telleria, Raul Orduna-Urrutia | Published: 2020-07-02
Opportunities and Challenges in Deep Learning Adversarial Robustness: A Survey
Authors: Samuel Henrique Silva, Peyman Najafirad | Published: 2020-07-01 | Updated: 2020-07-03
A Le Cam Type Bound for Adversarial Learning and Applications
Authors: Qiuling Xu, Kevin Bello, Jean Honorio | Published: 2020-07-01 | Updated: 2021-02-10
FDA3 : Federated Defense Against Adversarial Attacks for Cloud-Based IIoT Applications
Authors: Yunfei Song, Tian Liu, Tongquan Wei, Xiangfeng Wang, Zhe Tao, Mingsong Chen | Published: 2020-06-28
Orthogonal Deep Models As Defense Against Black-Box Attacks
Authors: Mohammad A. A. K. Jalwana, Naveed Akhtar, Mohammed Bennamoun, Ajmal Mian | Published: 2020-06-26
Proper Network Interpretability Helps Adversarial Robustness in Classification
Authors: Akhilan Boopathy, Sijia Liu, Gaoyuan Zhang, Cynthia Liu, Pin-Yu Chen, Shiyu Chang, Luca Daniel | Published: 2020-06-26 | Updated: 2020-10-21