Attack Strength vs. Detectability Dilemma in Adversarial Machine Learning

Christopher Frederickson, Michael Moore, Glenn Dawson, Robi Polikar

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

6 Scopus citations

Abstract

As the prevalence and everyday use of machine learning algorithms, along with our reliance on these algorithms grow dramatically, so do the efforts to attack and undermine these algorithms with malicious intent, resulting in a growing interest in adversarial machine learning. A number of approaches have been developed that can render a machine learning algorithm ineffective through poisoning or other types of attacks. Most attack algorithms typically use sophisticated optimization approaches, whose objective function is designed to cause maximum damage to accuracy or performance of the algorithm with respect to some task. In this effort, we show that while such an objective function is indeed brutally effective in causing maximum damage on an embedded feature selection task, it often results in an attack mechanism that can be easily detected with an embarrassingly simple novelty or outlier detection algorithm. We then propose an equally simple yet elegant solution by adding a regularization term to the attacker's objective function that penalizes outlying attack points.

Original languageEnglish (US)
Title of host publication2018 International Joint Conference on Neural Networks, IJCNN 2018 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509060146
DOIs
StatePublished - Oct 10 2018
Event2018 International Joint Conference on Neural Networks, IJCNN 2018 - Rio de Janeiro, Brazil
Duration: Jul 8 2018Jul 13 2018

Publication series

NameProceedings of the International Joint Conference on Neural Networks
Volume2018-July

Other

Other2018 International Joint Conference on Neural Networks, IJCNN 2018
Country/TerritoryBrazil
CityRio de Janeiro
Period7/8/187/13/18

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Attack Strength vs. Detectability Dilemma in Adversarial Machine Learning'. Together they form a unique fingerprint.

Cite this