Security of neuromorphic computing: Thwarting learning attacks using memristor's obsolescence effect
Publication
, Conference
Yang, C; Liu, B; Li, H; Chen, Y; Wen, W; Barnell, M; Wu, Q; Rajendran, J
Published in: IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD
November 7, 2016
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.
Duke Scholars
Published In
IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD
DOI
ISSN
1092-3152
Publication Date
November 7, 2016
Volume
07-10-November-2016
Citation
APA
Chicago
ICMJE
MLA
NLM
Yang, C., Liu, B., Li, H., Chen, Y., Wen, W., Barnell, M., … Rajendran, J. (2016). Security of neuromorphic computing: Thwarting learning attacks using memristor's obsolescence effect. In IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD (Vol. 07-10-November-2016). https://doi.org/10.1145/2966986.2967074
Yang, C., B. Liu, H. Li, Y. Chen, W. Wen, M. Barnell, Q. Wu, and J. Rajendran. “Security of neuromorphic computing: Thwarting learning attacks using memristor's obsolescence effect.” In IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD, Vol. 07-10-November-2016, 2016. https://doi.org/10.1145/2966986.2967074.
Yang C, Liu B, Li H, Chen Y, Wen W, Barnell M, et al. Security of neuromorphic computing: Thwarting learning attacks using memristor's obsolescence effect. In: IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD. 2016.
Yang, C., et al. “Security of neuromorphic computing: Thwarting learning attacks using memristor's obsolescence effect.” IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD, vol. 07-10-November-2016, 2016. Scopus, doi:10.1145/2966986.2967074.
Yang C, Liu B, Li H, Chen Y, Wen W, Barnell M, Wu Q, Rajendran J. Security of neuromorphic computing: Thwarting learning attacks using memristor's obsolescence effect. IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD. 2016.
Published In
IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD
DOI
ISSN
1092-3152
Publication Date
November 7, 2016
Volume
07-10-November-2016