Challenges and New Directions for AI and Hardware Security

Benjamin Tan, Ramesh Karri

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

Abstract

Artificial Intelligence (AI) and Machine Learning (ML) techniques have found use in many fields, including hardware-based security defenses and novel threats to hardware security. In this paper, we briefly examine the growing overlap between AI/ML and hardware for security, where AI/ML techniques provide practitioners with new ways to monitor runtime behavior but also provide new tools for attackers to steal secret information. We also explore how AI/ML is reshaping concerns for improving the security of hardware, particularly as AI/ML appear throughout the design flow. While AI/ML techniques contribute towards better hardware Trojan detection, improved design turnaround time, and design space exploration, such techniques may also introduce new threat vectors into the supply chain. With these in mind, we present some potential challenges and new directions at these intersections, giving new insights into how hardware security, alongside AI/M,L advances.

Original languageEnglish (US)
Title of host publication2020 IEEE 63rd International Midwest Symposium on Circuits and Systems, MWSCAS 2020 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages277-280
Number of pages4
ISBN (Electronic)9781538629161
DOIs
StatePublished - Aug 2020
Event63rd IEEE International Midwest Symposium on Circuits and Systems, MWSCAS 2020 - Springfield, United States
Duration: Aug 9 2020Aug 12 2020

Publication series

NameMidwest Symposium on Circuits and Systems
Volume2020-August
ISSN (Print)1548-3746

Conference

Conference63rd IEEE International Midwest Symposium on Circuits and Systems, MWSCAS 2020
CountryUnited States
CitySpringfield
Period8/9/208/12/20

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Challenges and New Directions for AI and Hardware Security'. Together they form a unique fingerprint.

  • Cite this

    Tan, B., & Karri, R. (2020). Challenges and New Directions for AI and Hardware Security. In 2020 IEEE 63rd International Midwest Symposium on Circuits and Systems, MWSCAS 2020 - Proceedings (pp. 277-280). [9184612] (Midwest Symposium on Circuits and Systems; Vol. 2020-August). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MWSCAS48704.2020.9184612