Trust but Verify: An Information-Theoretic Explanation for the Adversarial Fragility of Machine Learning Systems, and a General Defense against Adversarial Attacks

Authors: Jirong Yi, Hui Xie, Leixin Zhou, Xiaodong Wu, Weiyu Xu, Raghuraman Mudumbai | Published: 2019-05-25

Rethinking Softmax Cross-Entropy Loss for Adversarial Robustness

Authors: Tianyu Pang, Kun Xu, Yinpeng Dong, Chao Du, Ning Chen, Jun Zhu | Published: 2019-05-25 | Updated: 2020-02-20

Enhancing Adversarial Defense by k-Winners-Take-All

Authors: Chang Xiao, Peilin Zhong, Changxi Zheng | Published: 2019-05-25 | Updated: 2019-10-29

The advantages of multiple classes for reducing overfitting from test set reuse

Authors: Vitaly Feldman, Roy Frostig, Moritz Hardt | Published: 2019-05-24

Devil in the Detail: Attack Scenarios in Industrial Applications

Authors: Simon D. Duque Anton, Alexander Hafner, Hans Dieter Schotten | Published: 2019-05-24

Privacy Risks of Securing Machine Learning Models against Adversarial Examples

Authors: Liwei Song, Reza Shokri, Prateek Mittal | Published: 2019-05-24 | Updated: 2019-08-25

Partially Encrypted Machine Learning using Functional Encryption

Authors: Theo Ryffel, Edouard Dufour-Sans, Romain Gay, Francis Bach, David Pointcheval | Published: 2019-05-24 | Updated: 2021-09-23

Power up! Robust Graph Convolutional Network via Graph Powering

Authors: Ming Jin, Heng Chang, Wenwu Zhu, Somayeh Sojoudi | Published: 2019-05-24 | Updated: 2021-09-21

Robust Attribution Regularization

Authors: Jiefeng Chen, Xi Wu, Vaibhav Rastogi, Yingyu Liang, Somesh Jha | Published: 2019-05-23 | Updated: 2019-10-26

Thwarting finite difference adversarial attacks with output randomization

Authors: Haidar Khan, Daniel Park, Azer Khan, Bülent Yener | Published: 2019-05-23