Can I read DeepStrike: Remotely-Guided Fault Injection Attacks on DNN Accelerator in Cloud-FPGA on EtoBox?

DeepStrike: Remotely-Guided Fault Injection Attacks on DNN Accelerator in Cloud-FPGA by Luo, Yukui; Gongye, Cheng; Fei, Yunsi; Xu, Xiaolin is a scholarly article available to read on EtoBox.

What is DeepStrike: Remotely-Guided Fault Injection Attacks on DNN Accelerator in Cloud-FPGA about?

As Field-programmable gate arrays (FPGAs) are widely adopted in clouds to accelerate Deep Neural Networks (DNN), such virtualization environments have posed many new security issues. This work investigates the integrity of DNN FPGA accelerators in clouds. It proposes DeepStrike, a remotely-guided attack based on power glitching fault injections targeting DNN execution. We characterize the vulnerabilities of different DNN layers against fault injections on FPGAs and leverage time-to-digital converter (TDC) sensors to precisely control the timing of fault injections. Experimental results show that our proposed attack can successfully disrupt the FPGA DSP kernel and misclassify the target victim DNN application.

Author

Luo, Yukui; Gongye, Cheng; Fei, Yunsi; Xu, Xiaolin

Published

2021

Language

EN