Robust Machine Learning via Privacy/Rate-Distortion Theory
Authors: Ye Wang, Shuchin Aeron, Adnan Siraj Rakin, Toshiaki Koike-Akino, Pierre Moulin | Published: 2020-07-22 | Updated: 2021-05-18
最適化問題
Improved Adversarial Training via Learned Optimizer
Authors: Yuanhao Xiong, Cho-Jui Hsieh | Published: 2020-04-25
A Black-box Adversarial Attack Strategy with Adjustable Sparsity and Generalizability for Deep Image Classifiers
Authors: Arka Ghosh, Sankha Subhra Mullick, Shounak Datta, Swagatam Das, Rammohan Mallipeddi, Asit Kr. Das | Published: 2020-04-24 | Updated: 2021-09-09
Towards Federated Learning With Byzantine-Robust Client Weighting
Authors: Amit Portnoy, Yoav Tirosh, Danny Hendler | Published: 2020-04-10 | Updated: 2021-05-18
Private Knowledge Transfer via Model Distillation with Generative Adversarial Networks
Authors: Di Gao, Cheng Zhuo | Published: 2020-04-05
HYDRA: Pruning Adversarially Robust Neural Networks
Authors: Vikash Sehwag, Shiqi Wang, Prateek Mittal, Suman Jana | Published: 2020-02-24 | Updated: 2020-11-10
Improving the Tightness of Convex Relaxation Bounds for Training Certifiably Robust Classifiers
Authors: Chen Zhu, Renkun Ni, Ping-yeh Chiang, Hengduo Li, Furong Huang, Tom Goldstein | Published: 2020-02-22
Black-Box Certification with Randomized Smoothing: A Functional Optimization Based Framework
Authors: Dinghuai Zhang, Mao Ye, Chengyue Gong, Zhanxing Zhu, Qiang Liu | Published: 2020-02-21 | Updated: 2020-10-20
On the Decision Boundaries of Neural Networks: A Tropical Geometry Perspective
Authors: Motasem Alfarra, Adel Bibi, Hasan Hammoud, Mohamed Gaafar, Bernard Ghanem | Published: 2020-02-20 | Updated: 2022-08-22
Training Provably Robust Models by Polyhedral Envelope Regularization
Authors: Chen Liu, Mathieu Salzmann, Sabine Süsstrunk | Published: 2019-12-10 | Updated: 2021-09-20