Open Access. Powered by Scholars. Published by Universities.®
VLSI and Circuits, Embedded and Hardware Systems Commons™
Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 2 of 2
Full-Text Articles in VLSI and Circuits, Embedded and Hardware Systems
Towards Multipronged On-Chip Memory And Data Protection From Verification To Design And Test, Senwen Kan, Jennifer Dworak
Towards Multipronged On-Chip Memory And Data Protection From Verification To Design And Test, Senwen Kan, Jennifer Dworak
Computer Science and Engineering Theses and Dissertations
Modern System on Chips (SoCs) generally include embedded memories, and these memories may be vulnerable to malicious attacks such as hardware trojan horses (HTHs), test access port exploitation, and malicious software. This dissertation contributes verification as well as design obfuscation solutions aimed at design level detection of memory HTH circuits as well as obfuscation to prevent HTH triggering for embedded memory during functional operation. For malicious attack vectors stemming from test/debug interfaces, this dissertation presents novel solutions that enhance design verification and securitization of an IJTAG based test access interface. Such solutions can enhance SoC protection by preventing memory test …
Algorithm Optimization And Hardware Acceleration For Machine Learning Applications On Low-Energy Systems, Jianchi Sun
Algorithm Optimization And Hardware Acceleration For Machine Learning Applications On Low-Energy Systems, Jianchi Sun
All Dissertations
Machine learning (ML) has been extensively employed for strategy optimization, decision making, data classification, etc. While ML shows great triumph in its application field, the increasing complexity of the learning models introduces neoteric challenges to the ML system designs. On the one hand, the applications of ML on resource-restricted terminals, like mobile computing and IoT devices, are prevented by the high computational complexity and memory requirement. On the other hand, the massive parameter quantity for the modern ML models appends extra demands on the system's I/O speed and memory size. This dissertation investigates feasible solutions for those challenges with software-hardware …