DeepStrike: Remotely-Guided Fault Injection Attacks on DNN Accelerator in Cloud-FPGA

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 at...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	2021 58th ACM/IEEE Design Automation Conference (DAC) S. 295 - 300
Hauptverfasser:	Luo, Yukui, Gongye, Cheng, Fei, Yunsi, Xu, Xiaolin
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 05.12.2021
Schlagworte:	Cloud computing Design automation Field programmable gate arrays Logic gates Neural network hardware Neural networks Physical layer security Security Sensor phenomena and characterization Timing
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	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:	10.1109/DAC18074.2021.9586262