A Microprocessor Protection Architecture against Hardware Trojans in Memories

Software exploitable Hardware Trojan Horses (HWTs) have been currently inserted in commercial CPUs and, very recently, in memories. Such attacks may allow malicious users to run their own software or to gain unauthorized privileges over the system. Therefore, HWTs are nowadays considered a serious t...

Full description

Saved in:
Bibliographic Details
Published in:2020 15th Design & Technology of Integrated Systems in Nanoscale Era (DTIS) pp. 1 - 6
Main Authors: Bolat, Alperen, Cassano, Luca, Reviriego, Pedro, Ergin, Oguz, Ottavi, Marco
Format: Conference Proceeding
Language:English
Published: IEEE 01.04.2020
Subjects:
Bloom Filter
Computer architecture
Field programmable gate arrays
Filters
Flip-flops
Frequency measurement
Hardware Security
Hardware Trojan Horses
Microprocessor-based System
Microprocessors
Proposals
Protection
RISC-V
Software
Trojan horses
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Software exploitable Hardware Trojan Horses (HWTs) have been currently inserted in commercial CPUs and, very recently, in memories. Such attacks may allow malicious users to run their own software or to gain unauthorized privileges over the system. Therefore, HWTs are nowadays considered a serious threat both from academy and industry. This paper presents a protection architecture meant to shield the communication between the CPU and the memory in a microprocessor-based system. The architecture aims at detecting the activation on HWTs infesting the instruction and data memories of the system. Our proposal relies on the use of Bloom Filters (BFs) that are included in ad-hoc designed checkers and integrated in the protection architecture. BFs guarantee zero false alarms and a small (and configurable) percentage of undetected alarms. We applied the protection architecture to a case study system based on a RISC-V microprocessor implemented on an FPGA and running a set of software benchmarks. Our proposal demonstrated to be able to detect more than 99% of possible HWTs activations with zero false alarms. We measured a lookup table overhead ranging from 0.68% up to 10.52% and a flip-flop overhead between 0.68% and 0.99%, and with no working frequency reduction.
DOI:10.1109/DTIS48698.2020.9080961