TY - GEN
T1 - Hardware Trojan Attacks on the Reconfigurable Interconnections of Convolutional Neural Networks Accelerators
AU - Yang, Chen
AU - Hou, Jia
AU - Wu, Minshun
AU - Mei, Kuizhi
AU - Geng, Li
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/11/3
Y1 - 2020/11/3
N2 - 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. Due to ubiquitous deployment of these AI systems, a strong incentive rises for adversaries to attack CNN accelerators via hardware Trojan, which is one of the most important attack models in hardware security domain. This paper proposed a hardware Trojan that attacks the crucial component in CNN accelerators, i.e., reconfigurable interconnection network. This hardware Trojan changes the data paths under activation, resulting in incorrect connection of the arithmetic circuit, thereby causing wrong convolutional computation. Experimental results show that with increasing only 0.27% hardware overhead to the accelerator, the proposed hardware Trojan can be activated to cause a degradation of inference accuracy by 8.93% 86.20%.
AB - 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. Due to ubiquitous deployment of these AI systems, a strong incentive rises for adversaries to attack CNN accelerators via hardware Trojan, which is one of the most important attack models in hardware security domain. This paper proposed a hardware Trojan that attacks the crucial component in CNN accelerators, i.e., reconfigurable interconnection network. This hardware Trojan changes the data paths under activation, resulting in incorrect connection of the arithmetic circuit, thereby causing wrong convolutional computation. Experimental results show that with increasing only 0.27% hardware overhead to the accelerator, the proposed hardware Trojan can be activated to cause a degradation of inference accuracy by 8.93% 86.20%.
UR - https://www.scopus.com/pages/publications/85099264543
U2 - 10.1109/ICSICT49897.2020.9278162
DO - 10.1109/ICSICT49897.2020.9278162
M3 - 会议稿件
AN - SCOPUS:85099264543
T3 - 2020 IEEE 15th International Conference on Solid-State and Integrated Circuit Technology, ICSICT 2020 - Proceedings
BT - 2020 IEEE 15th International Conference on Solid-State and Integrated Circuit Technology, ICSICT 2020 - Proceedings
A2 - Yu, Shaofeng
A2 - Zhu, Xiaona
A2 - Tang, Ting-Ao
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 15th IEEE International Conference on Solid-State and Integrated Circuit Technology, ICSICT 2020
Y2 - 3 November 2020 through 6 November 2020
ER -