Security of neuromorphic computing Conference Paper uri icon

abstract

  • 2016 ACM. Neuromorphic architectures are widely used in many applications for advanced data processing, and often implements proprietary algorithms. In this work, we prevent an attacker with physical access from learning the proprietary algorithm implemented by the neuromorphic hardware. For this purpose, we leverage the obsolescence effect in memristors to judiciously reduce the accuracy of outputs for any unauthorized user. For a legitimate user, we regulate the obsolescence effect, thereby controlling the accuracy of outputs. We also analyze the security vs. cost trade-offs for different applications. Our methodology is compatible with mainstream classification applications, memristor devices, and security and performance constraints.

name of conference

  • Proceedings of the 35th International Conference on Computer-Aided Design

published proceedings

  • Proceedings of the 35th International Conference on Computer-Aided Design

author list (cited authors)

  • Yang, C., Liu, B., Li, H., Chen, Y., Wen, W., Barnell, M., Wu, Q., & Rajendran, J.

citation count

  • 12

complete list of authors

  • Yang, Chaofei||Liu, Beiye||Li, Hai||Chen, Yiran||Wen, Wujie||Barnell, Mark||Wu, Qing||Rajendran, Jeyavijayan

publication date

  • January 2016