EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PowerGAN: A Machine Learning Approach for Power Side‐Channel Attack on Compute‐in‐Memory Accelerators

Ziyu Wang, Yuting Wu, Yongmo Park, Sangmin Yoo, Xinxin Wang, Jason K. Eshraghian, Wei D. Lu

Advanced Intelligent Systems · 2023-12 · 5 (12)

DOI: 10.1002/aisy.202300313 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Intelligent Systems, online erschienen am 22.09.2023. Verfasst von Ziyu Wang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Semiconductor Research Corporation, National Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Analog compute‐in‐memory (CIM) systems are promising candidates for deep neural network (DNN) inference acceleration. However, as the use of DNNs expands, protecting user input privacy has become increasingly important. Herein, a potential security vulnerability is identified wherein an adversary can reconstruct the user's private input data from a power side‐channel attack even without knowledge of the stored DNN model. An attack approach using a generative adversarial network is developed to achieve high‐quality data reconstruction from power leakage measurements. The analyses show that the attack methodology is effective in reconstructing user input data from power leakage of the analog CIM accelerator, even at large noise levels and after countermeasures. To demonstrate the efficacy of the proposed approach, an example of CIM inference of U‐Net for brain tumor detection is attacked, and the original magnetic resonance imaging medical images can be successfully reconstructed even at a noise level of 20% standard deviation of the maximum power signal value. This study highlights a potential security vulnerability in emerging analog CIM accelerators and raises awareness of needed safety features to protect user privacy in such systems.

Förderung

  • Semiconductor Research Corporation
  • National Science Foundation

Zitieren

APA

Wang, Z., Wu, Y., Park, Y., Yoo, S., Wang, X., Eshraghian, J. K., & Lu, W. D. (2023). PowerGAN: A Machine Learning Approach for Power Side‐Channel Attack on Compute‐in‐Memory Accelerators. Advanced Intelligent Systems, 5(12). https://doi.org/10.1002/aisy.202300313

Vancouver

Wang Z, Wu Y, Park Y, Yoo S, Wang X, Eshraghian JK, et al. PowerGAN: A Machine Learning Approach for Power Side‐Channel Attack on Compute‐in‐Memory Accelerators. Advanced Intelligent Systems. 2023;5(12). doi:10.1002/aisy.202300313

BibTeX
@article{Wang2023,
  author = {Wang, Ziyu and Wu, Yuting and Park, Yongmo and Yoo, Sangmin and Wang, Xinxin and Eshraghian, Jason K. and Lu, Wei D.},
  title = {PowerGAN: A Machine Learning Approach for Power Side‐Channel Attack on Compute‐in‐Memory Accelerators},
  journal = {Advanced Intelligent Systems},
  year = {2023},
  volume = {5},
  number = {12},
  doi = {10.1002/aisy.202300313}
}
Kostenlos starten →