When Explainability Meets Adversarial Learning: Detecting Adversarial Examples using SHAP Signatures

Gil Fidel, Ron Bitton, Asaf Shabtai

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

21 Scopus citations

Abstract

State-of-the-art deep neural networks (DNNs) are highly effective in solving many complex real-world problems. However, these models are vulnerable to adversarial perturbation attacks, and despite the plethora of research in this domain, to this day, adversaries still have the upper hand in the cat and mouse game of adversarial example generation methods vs. detection and prevention methods. In this research, we present a novel detection method that uses Shapley Additive Explanations (SHAP) values computed for the internal layers of a DNN classifier to discriminate between normal and adversarial inputs. We evaluate our method by building an extensive dataset of adversarial examples over the popular CIFAR-10 and MNIST datasets, and training a neural network-based detector to distinguish between normal and adversarial inputs. We evaluate our detector against adversarial examples generated by diverse state-of-the-art attacks and demonstrate its high detection accuracy and strong generalization ability to adversarial inputs generated with different attack methods.

Original languageEnglish
Title of host publication2020 International Joint Conference on Neural Networks, IJCNN 2020 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728169262
DOIs
StatePublished - 1 Jul 2020
Event2020 International Joint Conference on Neural Networks, IJCNN 2020 - Virtual, Glasgow, United Kingdom
Duration: 19 Jul 202024 Jul 2020

Publication series

NameProceedings of the International Joint Conference on Neural Networks

Conference

Conference2020 International Joint Conference on Neural Networks, IJCNN 2020
Country/TerritoryUnited Kingdom
CityVirtual, Glasgow
Period19/07/2024/07/20

Keywords

  • Adversarial Learning
  • Deep Learning
  • Explainable AI
  • SHAP

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'When Explainability Meets Adversarial Learning: Detecting Adversarial Examples using SHAP Signatures'. Together they form a unique fingerprint.

Cite this