EVHA: Explainable Vision System for Hardware Testing and Assurance-An Overview

被引:6
作者
Al Hasan, Md. Mahfuz [1 ]
Mostafiz, Mohammad Tahsin [1 ]
Le, Thomas An [1 ]
Julia, Jake [1 ]
Vashistha, Nidish [1 ]
Taheri, Shayan [1 ]
Asadizanjani, Navid [1 ]
机构
[1] Univ Florida, Florida Inst Cybersecur Res, 300 SW 13th St,POB 113150, Gainesville, FL 32601 USA
关键词
Hardware security and trust; physical inspection and assurance; hardware Trojan; semi-invasive methods; scanning electron microscopy; Artificial Intelligence; computer vision; convolutional neural networks; end-to-end learning; synthetic image generation; generative adversarial networks; self-supervised learning; contrastive learning; PREVENT;
D O I
10.1145/3590772
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Due to the ever-growing demands for electronic chips in different sectors, semiconductor companies have been mandated to offshore their manufacturing processes. This unwanted matter has made security and trustworthiness of their fabricated chips concerning and has caused the creation of hardware attacks. In this condition, different entities in the semiconductor supply chain can act maliciously and execute an attack on the design computing layers, from devices to systems. Our attack is a hardware Trojan that is inserted during mask generation/fabrication in an untrusted foundry. The Trojan leaves a footprint in the fabrication through addition, deletion, or change of design cells. To tackle this problem, we propose EVHA (Explainable Vision System for Hardware Testing and Assurance) in this work, which can detect the smallest possible change to a design in a low-cost, accurate, and fast manner. The inputs to this system are scanning electron microscopy images acquired from the integrated circuits under examination. The system output is the determination of integrated circuit status in terms of having any defect and/or hardware Trojan through addition, deletion, or change in the design cells at the cell level. This article provides an overview on the design, development, implementation, and analysis of our defense system.
引用
收藏
页数:25
相关论文
共 35 条
[1]   Generative Adversarial Network for Integrated Circuits Physical Assurance Using Scanning Electron Microscopy [J].
Al Hasan, Md Mahfuz ;
Vashistha, Nidish ;
Taheri, Shayan ;
Tehranipoor, Mark ;
Asadizanjani, Navid .
2021 IEEE INTERNATIONAL SYMPOSIUM ON THE PHYSICAL AND FAILURE ANALYSIS OF INTEGRATED CIRCUITS (IPFA), 2021,
[2]  
Alam Syed, 2021, HARNESSING POWER SEM
[3]  
Bao C, 2015, INT SYM QUAL ELECT, P47
[4]  
Bridle J. S, 1989, P 2 INT C NEURAL INF, P211
[5]  
Chen FQ, 2017, IEEE INT SYMP CIRC S
[6]   Exploring Simple Siamese Representation Learning [J].
Chen, Xinlei ;
He, Kaiming .
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, :15745-15753
[7]  
Du H., 2020, J PHYS C SER, V1486
[8]  
Hasegawa K, 2017, IEEE INT SYMP CIRC S, P2154
[9]   Deep Residual Learning for Image Recognition [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778
[10]  
Jin X., 2011, Encyclopedia of Machine Learning