Abstract

Deep neural networks outperform their contemporary peer models for computer vision tasks. These models are complex and challenging to interpret for practitioners. As more and more learning algorithms are deployed in real-world applications, model interpretability has become quite essential. Incidentally, Model interpretability is quite relevant to the case of deep neural networks as they can fall prey to adversarial attacks crafted by adversaries. In this paper, we launch an iterative targeted attack using a set of image classes on base architectures and interpret the results by applying an explanation algorithm before and after the attack. This process leads us to some valuable conclusions regarding the effects of the attack on the explanation methods and how explanation methods can be made to have more adversarial robustness.

Original languageEnglish
Title of host publicationINDICON 2022 - 2022 IEEE 19th India Council International Conference
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665473507
DOIs
Publication statusPublished - 2022
Event19th IEEE India Council International Conference, INDICON 2022 - Kochi, India
Duration: 24-11-202226-11-2022

Publication series

NameINDICON 2022 - 2022 IEEE 19th India Council International Conference

Conference

Conference19th IEEE India Council International Conference, INDICON 2022
Country/TerritoryIndia
CityKochi
Period24-11-2226-11-22

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Energy Engineering and Power Technology
  • Renewable Energy, Sustainability and the Environment
  • Electrical and Electronic Engineering
  • Safety, Risk, Reliability and Quality
  • Modelling and Simulation

Fingerprint

Dive into the research topics of 'Explainability of Image Classifiers for Targeted Adversarial Attack'. Together they form a unique fingerprint.

Cite this