Micromachines · 2024 · 10 citations · 50 references
EngineeringComputer EngineeringComputer ScienceComputer SecurityField-programmable Gate ArraysReconfigurable ComputingField-programmable Gate Array ArchitectureFpga ArchitectureHardware AccelerationHardware TrojansPhysical Unclonable FunctionsReconfigurable AcceleratorsHardware Trojan CountermeasuresHardware Trojan DesignHardware Trojan DetectionHardware Trojan ResistanceIntegrated Circuit TrojansPhysically Unclonable FunctionsReconfigurable InterconnectsSecurity Of Ai Systems
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.
50
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Ross Girshick, Jeff Donahue, Trevor Darrell et al. · 2014 · 31.8K citations
Learning Deconvolution Network for Semantic Segmentation
Hyeonwoo Noh, Seunghoon Hong, Bohyung Han · 2015 · 4K citations
Ravikanth Pappu, Ben Recht, Jason Taylor et al. · Science · 2002 · 2K citations · Full text
Trojan Detection using IC Fingerprinting
Dakshi Agrawal, Selçuk Baktır, Deniz Karakoyunlu et al. · 2007 · 778 citations