Enhancing robustness of machine learning systems via data transformations

• Published in: 2018 52nd Annual Conference on Information Sciences and Systems (CISS) pp. 1 - 5
• Main Authors: Bhagoji, Arjun Nitin, Cullina, Daniel, Sitawarin, Chawin, Mittal, Prateek
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.03.2018
• Subjects: Dimensionality reduction; Neural networks; Principal component analysis; Robustness; Support vector machines; Training

We propose the use of data transformations as a defense against evasion attacks on ML classifiers. We present and investigate strategies for incorporating a variety of data transformations including dimensionality reduction via Principal Component Analysis to enhance the resilience of machine learni...