Designing Adversarially Resilient Classifiers using Resilient Feature Engineering

• Main Authors: Eykholt, Kevin, Prakash, Atul
• Format: Journal Article
• Language: English
• Published: 17-12-2018
• Subjects: Computer Science - Cryptography and Security; Computer Science - Learning; Statistics - Machine Learning
• DOI: 10.48550/arxiv.1812.06626

We provide a methodology, resilient feature engineering, for creating
adversarially resilient classifiers. According to existing work, adversarial
attacks identify weakly correlated or non-predictive features learned by the
classifier during training and design the adversarial noise to utilize these
features. Therefore, highly predictive features should be used first during
classification in order to determine the set of possible output labels. Our
methodology focuses the problem of designing resilient classifiers into a
problem of designing resilient feature extractors for these highly predictive
features. We provide two theorems, which support our methodology. The Serial
Composition Resilience and Parallel Composition Resilience theorems show that
the output of adversarially resilient feature extractors can be combined to
create an equally resilient classifier. Based on our theoretical results, we
outline the design of an adversarially resilient classifier.