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 Dec 3;25(23):7369.
doi: 10.3390/s25237369.

Face Privacy Protection Method for Autonomous Sensors Based on Hierarchical Format-Preserving Encryption

Haojie Ji  1   2 , Long Jin  1 , Junjie Zhang  3 , Te Hu  1 , Chongshi Xin  1 , Yuchi Yao  1
Affiliations

Face Privacy Protection Method for Autonomous Sensors Based on Hierarchical Format-Preserving Encryption

Haojie Ji et al. Sensors (Basel). .

Abstract

Advanced sensors in connected automated vehicles (CAVs) increasingly collect facial biometric information for environmental perception, posing serious privacy leakage risks. However, existing privacy protection methods for automotive data primarily focus on strict security mechanisms and fail to fully balance data usability. This paper presents a hierarchical format-preserving encryption (H-FPE) method for face privacy protection in autonomous sensors. The proposed method constructs a privacy-preserving framework for face detection based on YOLOv11 by employing a region-specific encryption strategy where the encryption strength is tailored to the importance of different facial regions. The encryption algorithm employs SM4-based Feistel structures with pseudo-random functions to ensure RGB value constraints while maintaining image format integrity. Experimental evaluation results in diverse scenarios demonstrate that the proposed privacy encryption method achieves superior privacy protection performance. In terms of encryption strength, the method achieves entropy efficiency exceeding 98%, with an average entropy increase of 0.77 bits, representing an improvement of approximately 9.4% over the traditional thumbnail-preserving encryption (TPE) method. Considering the usability of downstream tasks, the proposed method preserves pedestrian detection performance, with F1-scores exceeding 97% in selected scenarios, demonstrating a 0.5% difference compared to TPE while providing substantially stronger privacy protection. The H-FPE method effectively balances privacy protection and functional usability, offering a robust solution for facial data protection in autonomous sensor applications while preserving essential detection capabilities.

Keywords: data security; face privacy; format-preserving encryption; functional usability; pedestrian detection.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure 1
Figure 1
Architecture diagram of a face privacy protection system based on H-FPE.
Figure 2
Figure 2
(a) Original image; (b) image encrypted by H-FPE; (c) image encrypted by TPE; (d) image encrypted by ideal TPE.
Figure 3
Figure 3
(a) Information entropy distribution comparison for scenario S1; (b) information entropy distribution comparison for scenario S2; (c) information entropy distribution comparison for scenario S3.
Figure 4
Figure 4
(a) Entropy transformation scatter comparison for scenario S1; (b) entropy transformation scatter comparison for scenario S2; (c) entropy transformation scatter comparison for scenario S3.
Figure 5
Figure 5
(a) CDF comparison of entropy values for scenario S1; (b) CDF comparison of entropy values for scenario S2; (c) CDF comparison of entropy values for scenario S3.
Figure 6
Figure 6
(a) Performance metric trend comparison for scenario S1; (b) performance metric trend comparison for scenario S2; (c) performance metric trend comparison for scenario S3.
Figure 7
Figure 7
(a) IOU threshold sensitivity comparison in scenario S1; (b) IOU threshold sensitivity comparison in scenario S2; (c) IOU threshold sensitivity comparison in scenario S3.
See this image and copyright information in PMC

References

    1. Fan J., Fan L., Ni Q., Wang J., Liu Y., Li R., Wang Y., Wang S. Perception and planning of intelligent vehicles based on BEV in extreme Off-Road scenarios. IEEE Trans. Intell. Veh. 2024;9:4568–4572. doi: 10.1109/TIV.2024.3392753. - DOI
    1. Falaschetti L., Manoni L., Palma L., Pierleoni P., Turchetti C. Embedded real-time vehicle and pedestrian detection using a compressed tiny YOLO v3 architecture. IEEE Trans. Intell. Transp. Syst. 2024;25:19399–19414. doi: 10.1109/TITS.2024.3447453. - DOI
    1. Irfan M.S., Dasgupta S., Rahman M. Toward transportation digital twin systems for traffic safety and mobility: A review. IEEE Internet Things J. 2024;11:24581–24603. doi: 10.1109/JIOT.2024.3395186. - DOI
    1. Chen X., Yin J., Tang K., Tian Y., Sun J. Vehicle trajectory reconstruction at signalized intersections under connected and automated vehicle environment. IEEE Trans. Intell. Transp. Syst. 2022;23:17986–18000. doi: 10.1109/TITS.2022.3150577. - DOI
    1. Zhao J., Yang X., Zhang C. Vehicle trajectory reconstruction for intersections: An integrated wavelet transform and Savitzky-Golay filter approach. Transp. A. 2024;20:2163207. doi: 10.1080/23249935.2022.2163207. - DOI

LinkOut - more resources