TY - GEN
T1 - Robust Machine Learning Systems
T2 - 24th IEEE International Symposium on On-Line Testing and Robust System Design, IOLTS 2018
AU - Hanif, Muhammad Abdullah
AU - Khalid, Faiq
AU - Putra, Rachmad Vidya Wicaksana
AU - Rehman, Semeen
AU - Shafique, Muhammad
N1 - Funding Information:
This Work is supported in parts by the German Research Foundation (DFG) as part of the GetSURE project in the scope of SPP-1500 (http://spp1500.itec.kit.edu # $% & '
Publisher Copyright:
© 2018 IEEE.
Copyright:
Copyright 2018 Elsevier B.V., All rights reserved.
PY - 2018/9/26
Y1 - 2018/9/26
N2 - 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.
AB - 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.
KW - Aging
KW - Deep Neural Networks
KW - DNNs
KW - Hardware
KW - Machine Learning
KW - Process Variations
KW - Reliability
KW - Security
KW - Soft Errors
UR - http://www.scopus.com/inward/record.url?scp=85052133733&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85052133733&partnerID=8YFLogxK
U2 - 10.1109/IOLTS.2018.8474192
DO - 10.1109/IOLTS.2018.8474192
M3 - Conference contribution
AN - SCOPUS:85052133733
T3 - 2018 IEEE 24th International Symposium on On-Line Testing and Robust System Design, IOLTS 2018
SP - 257
EP - 260
BT - 2018 IEEE 24th International Symposium on On-Line Testing and Robust System Design, IOLTS 2018
A2 - Maniatakos, Mihalis
A2 - Alexandrescu, Dan
A2 - Gizopoulos, Dimitris
A2 - Papavramidou, Panagiota
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 2 July 2018 through 4 July 2018
ER -