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

arXiv: https://arxiv.org/abs/2105.09453 · HTML: https://mlsanity.com/paper/2105.09453/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 May 2021.

## Built on by (most cited first, 4 of 4)

- [NNSplitter: An Active Defense Solution for DNN Model via Automated Weight Obfuscation](https://mlsanity.com/paper/2305.00097/) (2023)
- [Mercury: An Automated Remote Side-channel Attack to Nvidia Deep Learning Accelerator](https://mlsanity.com/paper/2308.01193/) (2023)
- [DeepNcode: Encoding-Based Protection against Bit-Flip Attacks on Neural Networks](https://mlsanity.com/paper/2405.13891/) (2024)
- [SoK: Colluding Adversaries in Machine Learning Pipelines](https://mlsanity.com/paper/2606.10091/) (2026)

## Abstract (arXiv)

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.