Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Aug 12;15(1):29528.
doi: 10.1038/s41598-025-14047-3.

Securing gait recognition with homomorphic encryption

Marina Banov  1   2 , Domagoj Pinčić  1 , Diego Sušanj  3 , Kristijan Lenac  4   5
Affiliations

Securing gait recognition with homomorphic encryption

Marina Banov et al. Sci Rep. .

Abstract

Biometric identification systems offer strong security by relying on unique personal traits. At the same time, they raise significant privacy concerns because compromised biometric data cannot be revoked. This paper explores the use of homomorphic encryption (HE) as a means to protect biometric data during classification and reduce the risk of exposing sensitive information. Our system comprises a feature extractor which operates locally and a classifier which processes encrypted data. We demonstrate the feasibility of our approach on a gait recognition task, employing a vision transformer as a feature extractor and training several HE-compatible classifiers. Through a comprehensive statistical analysis, we evaluate the impact of HE on accuracy and computational complexity, especially with different activation functions and their polynomial approximations. Our results demonstrate the feasibility of secure and accurate gait recognition using HE, while highlighting the trade-off between security and performance.

Keywords: Deep learning; Gait recognition; Homomorphic encryption; Privacy preserving computation; Secure biometrics.

PubMed Disclaimer

Conflict of interest statement

Declarations. Competing interests: The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
System architecture showing local encryption of biometric features and remote homomorphic classification.
Fig. 2
Fig. 2
Shared architecture of the five classifiers with different activation functions.
Fig. 3
Fig. 3
Our processing pipeline, including training and inference in the plaintext and encrypted domain.
Fig. 4
Fig. 4
Average processing times for single instance evaluation in the encrypted domain.
See this image and copyright information in PMC

References

    1. Munusamy, V. & Senthilkumar, S. Emerging trends in gait recognition based on deep learning: A survey. PeerJ Comput. Sci.10.7717/peerj-cs.2158 (2024). - PMC - PubMed
    1. Aung, S. T. Y. & Kusakunniran, W. A comprehensive review of gait analysis using deep learning approaches in criminal investigation. PeerJ Comput. Sci.10.7717/peerj-cs.2456 (2024). - PMC - PubMed
    1. Shen, C., Yu, S., Wang, J., Huang, G. Q. & Wang, L. A comprehensive survey on deep gait recognition: Algorithms, datasets, and challenges. IEEE Trans. Biometr. Behav. Identity Sci.10.1109/TBIOM.2024.3486345 (2025).
    1. Meden, B. et al. Privacy-enhancing face biometrics: A comprehensive survey. IEEE Trans. Inf. Forensics Secur.10.1109/TIFS.2021.3096024 (2021).
    1. Rivest, R. L., Shamir, A. & Adleman, L. A method for obtaining digital signatures and public-key cryptosystems. Commun. ACM10.1145/359340.359342 (1978).

LinkOut - more resources