Hardware Trojan Attacks on the Reconfigurable Interconnections of Field-Programmable Gate Array-Based Convolutional Neural Network Accelerators and a Physically Unclonable Function-Based Countermeasure Detection Technique

Abstract

Convolutional neural networks (CNNs) have demonstrated significant superiority in modern artificial intelligence (AI) applications. To accelerate the inference process of CNNs, reconfigurable CNN accelerators that support diverse networks are widely employed for AI systems. Given the ubiquitous deployment of these AI systems, there is a growing concern regarding the security of CNN accelerators and the potential attacks they may face, including hardware Trojans. This paper proposes a hardware Trojan designed to attack a crucial component of FPGA-based CNN accelerators: the reconfigurable interconnection network. Specifically, the hardware Trojan alters the data paths during activation, resulting in incorrect connections in the arithmetic circuit and consequently causing erroneous convolutional computations. To address this issue, the paper introduces a novel detection technique based on physically unclonable functions (PUFs) to safeguard the reconfigurable interconnection network against hardware Trojan attacks. Experimental results demonstrate that by incorporating a mere 0.27% hardware overhead to the accelerator, the proposed hardware Trojan can degrade the inference accuracy of popular neural network architectures, including LeNet, AlexNet, and VGG, by a significant range of 8.93% to 86.20%. The implemented arbiter-PUF circuit on a Xilinx Zynq XC7Z100 platform successfully detects the presence and location of hardware Trojans in a reconfigurable interconnection network. This research highlights the vulnerability of reconfigurable CNN accelerators to hardware Trojan attacks and proposes a promising detection technique to mitigate potential security risks. The findings underscore the importance of addressing hardware security concerns in the design and deployment of AI systems utilizing FPGA-based CNN accelerators.

Using Learning Focal Point Algorithm to Classify Emotional Intelligence

“…Furthermore, the article delves into a discourse on the design intricacies and mathematical theories that form the foundational framework of the LFP algorithm. This comprehensive discussion not only underscores the practical application of our research but also underscores the theoretical underpinnings that contribute to the efficacy and innovation of the proposed LFP layer in the realm of emotional intelligence for teacher robots [19], [20], [21].…”

Comprehensive Artificial Intelligence Vulnerability Taxonomy

“…Hardware Trojan Attack by Hou et al (2024) In their recent article published in Micromachines, Hou et al proceed to demonstrate a possible attack on Convolutional Neural Networks (CNN) through trojanized FPGA (Field Programmable Gate Array) hardware (Hou et al, 2024).…”