Enhancing robustness of machine learning systems via data transformations

Arjun Nitin Bhagoji, Daniel Cullina, Chawin Sitawarin, Prateek Mittal

Research output: Chapter in Book/Report/Conference proceedingConference contribution

23 Scopus citations

Abstract

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 learning, targeting both the classification and the training phase. We empirically evaluate and demonstrate the feasibility of linear transformations of data as a defense mechanism against evasion attacks using multiple real-world datasets. Our key findings are that the defense is (i) effective against the best known evasion attacks from the literature, resulting in a two-fold increase in the resources required by a white-box adversary with knowledge of the defense for a successful attack, (ii) applicable across a range of ML classifiers, including Support Vector Machines and Deep Neural Networks, and (iii) generalizable to multiple application domains, including image classification and human activity classification.

Original languageEnglish (US)
Title of host publication2018 52nd Annual Conference on Information Sciences and Systems, CISS 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-5
Number of pages5
ISBN (Electronic)9781538605790
DOIs
StatePublished - May 21 2018
Event52nd Annual Conference on Information Sciences and Systems, CISS 2018 - Princeton, United States
Duration: Mar 21 2018Mar 23 2018

Publication series

Name2018 52nd Annual Conference on Information Sciences and Systems, CISS 2018

Other

Other52nd Annual Conference on Information Sciences and Systems, CISS 2018
CountryUnited States
CityPrinceton
Period3/21/183/23/18

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Networks and Communications
  • Information Systems

Fingerprint Dive into the research topics of 'Enhancing robustness of machine learning systems via data transformations'. Together they form a unique fingerprint.

  • Cite this

    Bhagoji, A. N., Cullina, D., Sitawarin, C., & Mittal, P. (2018). Enhancing robustness of machine learning systems via data transformations. In 2018 52nd Annual Conference on Information Sciences and Systems, CISS 2018 (pp. 1-5). (2018 52nd Annual Conference on Information Sciences and Systems, CISS 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CISS.2018.8362326