DeepStrike: Remotely-Guided Fault Injection Attacks on DNN Accelerator in Cloud-FPGA
DeepStrike: Remotely-Guided Fault Injection Attacks on DNN Accelerator in Cloud-FPGA
复制标题
DeepStrike:对 Cloud-FPGA 中的 DNN 加速器进行远程引导故障注入攻击
DOI:
10.1109/dac18074.2021.9586262
复制
发表时间:
2021
期刊:
影响因子:
--
通讯作者:
Xiaolin Xu
中科院分区:
文献类型:
--
作者:
Yukui Luo;Cheng Gongye;Yunsi Fei;Xiaolin Xu
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.
DOI:
--
发表时间:
2020-11
期刊:
ArXiv
影响因子:
--
作者:
A. S. Rakin;Yukui Luo;Xiaolin Xu;Deliang Fan
通讯作者:
A. S. Rakin;Yukui Luo;Xiaolin Xu;Deliang Fan
DOI:
10.1109/fpl50879.2020.00046
发表时间:
2020
期刊:
2020 30th International Conference on Field-Programmable Logic and Applications (FPL
影响因子:
--
作者:
Provelengios, George;Holcomb, Daniel;Tessier, Russell
通讯作者:
Tessier, Russell