|Dr. Rajat Subhra Chakraborty, Dept. of Computer Science and Engineering, IIT Kharagpur, E-mail: firstname.lastname@example.org|
|Title: Hardware Security in the Context of Flash Memory: Can Machine Learning Help?
Abstract:Semiconductor non-volatile “flash memory” is envisaged to replace all other forms of commercially deployed non-volatile memory technology in the near future. However, with the large-scale adoption of a “horizontal” business model, modern semiconductor supply chain is plagued by recycled and counterfeit ICs, including flash memory chips.
Since flash memory modules have an inherently finite lifespan, detection of recycled flash memory chips before their deployment in safety-critical systems is important to prevent disastrous consequences. The state-of-art detection methods can detect flash memory modules between 0.05% to 3.00% of their lifespan as minimum usage duration, depending on the details of the flash memory chip. We examine the applicability of machine learning to improve the minimum usage duration detection accuracy between 0.05% to 0.96% of their lifespan, and also to accurately associate a flash memory IC with its manufacturer. Through detailed experimentation and comparison of detection results obtained using three popular supervised machine learning techniques (Support Vector Machines, Logistic Regression and Artificial Neural Networks), we demonstrate that usage of features composed of multiple characteristics of a given chip, rather than just a single property of a chip (as used in previous works), improves detection accuracy.
Rajat Subhra Chakraborty is currently an Associate Professor at CSE Department of IIT Kharagpur. He received his Ph.D. from Case Western Reserve University (U.S.A.) and B.E. from Jadavpur University. He has professional experience of working at National Semiconductor (Bangalore, India) and Advanced Micro Devices (AMD) (Santa Clara, USA). His research interests include Hardware Security, VLSI Design and Design Automation, Digital Content Protection and Digital Image Forensics. He holds 2 Granted U.S. patents, and has co-authored 6 books, 8 book chapters, and over 100 publications in international journals and conferences.
His work has received over 3600 citations till date, and a paper co-authored by him won the Best Paper Award at the IWDW’16 workshop. He has received several prestigious national and international awards such as IIT Kharagpur Outstanding Faculty Award (2018), IEI Youg Engineers Award (2016), IBM Shared University Research (SUR) Award (2015), Royal Academy of Engineering (U.K.) RECI Fellowship (2014) and IBM Faculty Award (2012). He is currently an Associate Editor of IEEE TCAD journal. Dr. Chakraborty is a Senior Member of IEEE and a Senior Member of ACM.