Secure human action recognition by encrypted neural network inference

Miran Kim (), Xiaoqian Jiang, Kristin Lauter, Elkhan Ismayilzada and Shayan Shams ()
Additional contact information
Miran Kim: Hanyang University
Xiaoqian Jiang: University of Texas Health Science Center
Kristin Lauter: Meta AI Research
Elkhan Ismayilzada: Ulsan National Institute of Science and Technology
Shayan Shams: San Jose State University

Nature Communications, 2022, vol. 13, issue 1, 1-13

Abstract: Abstract Advanced computer vision technology can provide near real-time home monitoring to support “aging in place” by detecting falls and symptoms related to seizures and stroke. Affordable webcams, together with cloud computing services (to run machine learning algorithms), can potentially bring significant social benefits. However, it has not been deployed in practice because of privacy concerns. In this paper, we propose a strategy that uses homomorphic encryption to resolve this dilemma, which guarantees information confidentiality while retaining action detection. Our protocol for secure inference can distinguish falls from activities of daily living with 86.21% sensitivity and 99.14% specificity, with an average inference latency of 1.2 seconds and 2.4 seconds on real-world test datasets using small and large neural nets, respectively. We show that our method enables a 613x speedup over the latency-optimized LoLa and achieves an average of 3.1x throughput increase in secure inference compared to the throughput-optimized nGraph-HE2.

Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-022-32168-5 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:13:y:2022:i:1:d:10.1038_s41467-022-32168-5

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-022-32168-5

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().