Robust Machine Learning Systems: Reliability and Security for Deep Neural Networks

Muhammad Abdullah Hanif, Faiq Khalid, Rachmad Vidya Wicaksana Putra, Semeen Rehman, Muhammad Shafique

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

Abstract

Machine learning is commonly being used in almost all the areas that involve advanced data analytics and intelligent control. From applications like Natural Language Processing (NLP) to autonomous driving are based upon machine learning algorithms. An increasing trend is observed in the use of Deep Neural Networks (DNNs) for such applications. While the slight inaccuracy in applications like NLP does not have any severe consequences, it is not the same for other safety-critical applications, like autonomous driving and smart healthcare, where a small error can lead to catastrophic effects. Apart from high-accuracy DNN algorithms, there is a significant need for robust machine learning systems and hardware architectures that can generate reliable and trustworthy results in the presence of hardware-level faults while also preserving security and privacy. This paper provides an overview of the challenges being faced in ensuring reliable and secure execution of DNNs. To address the challenges, we present several techniques for analyzing and mitigating the reliability and security threats in machine learning systems.

Original languageEnglish (US)
Title of host publication2018 IEEE 24th International Symposium on On-Line Testing and Robust System Design, IOLTS 2018
EditorsMihalis Maniatakos, Dan Alexandrescu, Dimitris Gizopoulos, Panagiota Papavramidou
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages257-260
Number of pages4
ISBN (Electronic)9781538659922
DOIs
StatePublished - Sep 26 2018
Externally publishedYes
Event24th IEEE International Symposium on On-Line Testing and Robust System Design, IOLTS 2018 - Platja D'Aro, Spain
Duration: Jul 2 2018Jul 4 2018

Publication series

Name2018 IEEE 24th International Symposium on On-Line Testing and Robust System Design, IOLTS 2018

Conference

Conference24th IEEE International Symposium on On-Line Testing and Robust System Design, IOLTS 2018
CountrySpain
CityPlatja D'Aro
Period7/2/187/4/18

Keywords

  • Aging
  • Deep Neural Networks
  • DNNs
  • Hardware
  • Machine Learning
  • Process Variations
  • Reliability
  • Security
  • Soft Errors

ASJC Scopus subject areas

  • Hardware and Architecture
  • Software
  • Safety, Risk, Reliability and Quality

Fingerprint Dive into the research topics of 'Robust Machine Learning Systems: Reliability and Security for Deep Neural Networks'. Together they form a unique fingerprint.

Cite this