A3T: Adversarially Augmented Adversarial Training
Authors: Akram Erraqabi, Aristide Baratin, Yoshua Bengio, Simon Lacoste-Julien | Published: 2018-01-12
モデルの頑健性保証
Less is More: Culling the Training Set to Improve Robustness of Deep Neural Networks
Authors: Yongshuai Liu, Jiyu Chen, Hao Chen | Published: 2018-01-09 | Updated: 2018-12-08
Adversarial Perturbation Intensity Achieving Chosen Intra-Technique Transferability Level for Logistic Regression
Authors: Martin Gubri | Published: 2018-01-06
The Robust Manifold Defense: Adversarial Training using Generative Models
Authors: Ajil Jalal, Andrew Ilyas, Constantinos Daskalakis, Alexandros G. Dimakis | Published: 2017-12-26 | Updated: 2019-07-10
Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models
Authors: Wieland Brendel, Jonas Rauber, Matthias Bethge | Published: 2017-12-12 | Updated: 2018-02-16
CycleGAN, a Master of Steganography
Authors: Casey Chu, Andrey Zhmoginov, Mark Sandler | Published: 2017-12-08 | Updated: 2017-12-16
Generative Adversarial Perturbations
Authors: Omid Poursaeed, Isay Katsman, Bicheng Gao, Serge Belongie | Published: 2017-12-06 | Updated: 2018-07-06
Where Classification Fails, Interpretation Rises
Authors: Chanh Nguyen, Georgi Georgiev, Yujie Ji, Ting Wang | Published: 2017-12-02
Evaluating Robustness of Neural Networks with Mixed Integer Programming
Authors: Vincent Tjeng, Kai Xiao, Russ Tedrake | Published: 2017-11-20 | Updated: 2019-02-18
The best defense is a good offense: Countering black box attacks by predicting slightly wrong labels
Authors: Yannic Kilcher, Thomas Hofmann | Published: 2017-11-15