Towards Hardware Trojan Resilient Convolutional Neural Network Accelerators
Open Access
- 1 August 2025
- journal article
- research article
- Published by Springer Nature in Journal of Hardware and Systems Security
- Vol. 9 (3-4) , 89-106
Abstract
Convolutional neural network accelerators are increasingly used in safety–critical applications, including autonomous vehicles. Therefore, they are particularly vulnerable to hardware Trojan insertion, a security attack that takes place during the development of integrated circuits. This work presents for the first time a large-scale study of the impact of hardware Trojan insertion on convolutional neural network accelerators, focusing on those that use approximate commuting techniques, prevalent in embedded applications. We investigate three types of such networks, MobileNet V2, ShuffleNet V2, and GhostNet, trained in datasets of grayscale speed limit sign images and GTSRB. Our results show that certain parts of these architectures are more susceptible to hardware Trojan attacks, specifically a specific set of processing elements, referred to as “important” in the classification, ReLU6, and Max pooling layers, respectively. These findings are subsequently used to develop two countermeasures; the first relies on selective hardware redundancy (SHR), and the second uses a combination of hardware and time redundancy (SHTR). The proposed defenses are experimentally validated. Our results show that the SHR provides speedy recovery from an attack while incurring between 6 and 10% area overheads, whereas SHTR requires more time to detect the Trojan, and its area overhead is much smaller (~ 0.3%).Keywords
This publication has 50 references indexed in Scilit:
- A high-speed reusable quantized hardware accelerator design for CNN on constrained edge deviceDesign Automation for Embedded Systems, 2023
- CIST: A Threat Modelling Approach for Hardware Supply Chain Security2021
- Embedded System Design2021
- Ten years of hardware Trojans: a survey from the attacker's perspectiveIET Computers & Digital Techniques, 2020
- Sparse-YOLO: Hardware/Software Co-Design of an FPGA Accelerator for YOLOv2IEEE Access, 2020
- Security Threats and Countermeasures for Approximate Arithmetic Computing2020
- Design Space Exploration of Hardware Spiking Neurons for Embedded Artificial IntelligenceNeural Networks, 2020
- ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design2018
- Surveying the Hardware Trojan Threat Landscape for the Internet-of-ThingsJournal of Hardware and Systems Security, 2018
- System-level protection and hardware Trojan detection using weighted votingJournal of Advanced Research, 2014