A cryptographic approach to black box adversarial machine learning
Authors: Kevin Shi, Daniel Hsu, Allison Bishop | Published: 2019-06-07 | Updated: 2020-02-21
防御効果分析
Combatting Adversarial Attacks through Denoising and Dimensionality Reduction: A Cascaded Autoencoder Approach
Authors: Rajeev Sahay, Rehana Mahfuz, Aly El Gamal | Published: 2018-12-07
Adversarial Attacks, Regression, and Numerical Stability Regularization
Authors: Andre T. Nguyen, Edward Raff | Published: 2018-12-07
Enhancing Robustness of Machine Learning Systems via Data Transformations
Authors: Arjun Nitin Bhagoji, Daniel Cullina, Chawin Sitawarin, Prateek Mittal | Published: 2017-04-09 | Updated: 2017-11-29