Published February 3, 2020 | Version v1
Journal article Open

Robust Machine Learning Systems: Challenges, Current Trends, Perspectives, and the Road Ahead

Authors/Creators

  • 1. Technische Universität Wien
  • 2. University of Cyprus
  • 3. KIOS Center of Excellence, University of Cyprus
  • 4. ETH Zürich
  • 5. Hanyang University

Description

Currently, machine learning (ML) techniques are at the heart of smart cyber-physical systems (CPSs) and Internet-of-Things (loT). This article discusses various challenges and probable solutions for security attacks on these ML-inspired hardware and software techniques.

Notes

© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. https://www.ieee.org/publications_standards/publications/rights/rights_policies.html M. Shafique et al., "Robust Machine Learning Systems: Challenges,Current Trends, Perspectives, and the Road Ahead," in IEEE Design & Test, vol. 37, no. 2, pp. 30-57, April 2020, doi: 10.1109/MDAT.2020.2971217. https://ieeexplore.ieee.org/document/8979377

Files

2020_D_T.pdf

Files (18.4 MB)

Name Size Download all
md5:fdf3986e0f0c3dd348044776396deb86
18.4 MB Preview Download