Journal of Information Processing Systems

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Machine Learning-Based Reversible Chaotic Masking Method for User Privacy Protection in CCTV Environment

  • Jimin Ha (Dept. of Computer Science and Engineering, Seoul National University of Science & Technology (SeoulTech)) ;
  • Jungho Kang (Dept. of Information Security, Baewha Women's University) ;
  • Jong Hyuk Park (Dept. of Computer Science and Engineering, Seoul National University of Science & Technology (SeoulTech))
  • Received : 2023.09.20
  • Accepted : 2023.11.08
  • Published : 2023.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

In modern society, user privacy is emerging as an important issue as closed-circuit television (CCTV) systems increase rapidly in various public and private spaces. If CCTV cameras monitor sensitive areas or personal spaces, they can infringe on personal privacy. Someone's behavior patterns, sensitive information, residence, etc. can be exposed, and if the image data collected from CCTV is not properly protected, there can be a risk of data leakage by hackers or illegal accessors. This paper presents an innovative approach to "machine learning based reversible chaotic masking method for user privacy protection in CCTV environment." The proposed method was developed to protect an individual's identity within CCTV images while maintaining the usefulness of the data for surveillance and analysis purposes. This method utilizes a two-step process for user privacy. First, machine learning models are trained to accurately detect and locate human subjects within the CCTV frame. This model is designed to identify individuals accurately and robustly by leveraging state-of-the-art object detection techniques. When an individual is detected, reversible chaos masking technology is applied. This masking technique uses chaos maps to create complex patterns to hide individual facial features and identifiable characteristics. Above all, the generated mask can be reversibly applied and removed, allowing authorized users to access the original unmasking image.

Keywords

Acknowledgement

This work was supported by Korea Internet & Security Agency (KISA) grant funded by the Korea government (PIPC) (No. 1781000008, Real-time face de-identification technology that enables samesubject connection analysis in facial recognition CCTV).

References

  1. M. Sheeraz, M. A. Paracha, M. U. Haque, M. H. Durad, S. M. Mohsin, S. S. Band, and A. Mosavi, "Effective security monitoring using efficient SIEM architecture," Human-centric Computing and Information Sciences, vol. 13, article no. 17, 2023. https://doi.org/10.22967/HCIS.2023.13.017
  2. W. Ding, "Role of sensors based on machine learning health monitoring in athletes' wearable heart rate monitoring," Human-centric Computing and Information Sciences, vol. 13, article no. 16, 2023. https://doi.org/10.22967/HCIS.2023.13.016
  3. T. Jaichuen, N. Ren, P. Wongapinya, and S. Fugkeaw, "BLUR & TRACK: real-time face detection with immediate blurring and efficient tracking," in Proceedings of 2023 20th International Joint Conference on Computer Science and Software Engineering (JCSSE), Phitsanulok, Thailand, 2023, pp. 167-172. https://doi.org/10.1109/JCSSE58229.2023.10202064
  4. B. W. Kwon, P. K. Sharma, and J. H. Park, "CCTV-based multi-factor authentication system," Journal of Information Processing Systems, vol. 15, no. 4, pp. 904-919, 2019. https://doi.org/10.3745/JIPS.03.0127
  5. D. Lee and N. Park, "Blockchain based privacy preserving multimedia intelligent video surveillance using secure Merkle tree," Multimedia Tools and Applications, vol. 80, pp. 34517-34534, 2021. https://doi.org/10.1007/s11042-020-08776-y
  6. S. Prange, A. Shams, R. Piening, Y. Abdelrahman, and F. Alt, "Priview: exploring visualisations to support users' privacy awareness. In Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems, Yokohama, Japan, 2021, pp. 1-18. https://doi.org/10.1145/3411764.3445067
  7. Y. Beugin, Q. Burke, B. Hoak, R. Sheatsley, E. Pauley, G. Tan, S. R. Hussain, P. McDaniel, "Building a privacy-preserving smart camera system," 2022 [Online]. Available: https://arxiv.org/abs/2201.09338.
  8. E. Kristiani, Y. T. Tsan, P. Y. Liu, N. Y. Yen, and C. T. Yang, "Binary and multi-class assessment of face mask classification on edge AI using CNN and transfer learning," Human-centric Computing and Information Sciences, vol. 12, article no. 53, 2022. https://doi.org/10.22967/HCIS.2022.12.053
  9. E. Jasinskaite, "Combining deep privacy with an attribute-driven generative adversarial network to preserve gender and age in de-identified CCTV footage," M.S. thesis, University of Agder, Grimstad, Norway, 2021.
  10. Z. Zhong, Y. Du, Y. Zhou, J. Cao, and S. He, "Delving deep into pixelized face recovery and defense," Neurocomputing, vol. 513, pp. 233-246, 2022. https://doi.org/10.1016/j.neucom.2022.09.141
  11. J. Zhou and C. M. Pun, "Personal privacy protection via irrelevant faces tracking and pixelation in video live streaming," IEEE Transactions on Information Forensics and Security, vol. 16, pp. 1088-1103, 2020. https://doi.org/10.1109/TIFS.2020.3029913
  12. J. Zhou, C. M. Pun, and Y. Tong, "Privacy-sensitive objects pixelation for live video streaming," in Proceedings of the 28th ACM International Conference on Multimedia, Seattle, WA, USA, 2020, pp. 3025-3033. https://doi.org/10.1145/3394171.3413972
  13. L. Li, Z. Xia, A. Hadid, X. Jiang, H. Zhang, and X. Feng, "Replayed video attack detection based on motion blur analysis," IEEE Transactions on Information Forensics and Security, vol. 14, no. 9, pp. 2246-2261, 2019. https://doi.org/10.1109/TIFS.2019.2895212
  14. X. Hu, S. Peng, L. Wang, Z. Yang, and Z. Li, "Surveillance video face recognition with single sample per person based on 3D modeling and blurring," Neurocomputing, vol. 235, pp. 46-58, 2017. https://doi.org/10.1016/j.neucom.2016.12.059
  15. T. Rakhimzhanova, "Face and facial landmark detection for event-based imaging," M.S. thesis, School of Engineering and Digital Sciences, Nazarbayev University, Astana, Kazakhstan, 2023.
  16. S. S. Jang, C. J. Kim, S. Y. Hwang, M. J. Lee, and Y. G. Ha, "L-GAN: landmark-based generative adversarial network for efficient face de-identification," The Journal of Supercomputing, vol. 79, pp. 7132-7159, 2023. https://doi.org/10.1007/s11227-022-04954-x
  17. J. Lin, "Accurate and Fast mask recognition based on multiple color areas detection and face landmarks locating," in Proceedings of 2022 IEEE 22nd International Conference on Communication Technology (ICCT), Nanjing, China, 2022, pp. 1463-1467. https://doi.org/10.1109/ICCT56141.2022.10072864
  18. V. Bazarevsky, Y. Kartynnik, A. Vakunov, K. Raveendran, and M. Grundmann, "BlazeFace: sub-millisecond neural face detection on mobile GPUs," 2019 [Online]. Available: https://arxiv.org/abs/1907.05047.
  19. T. Mantoro and M. A. Ayu, "Multi-faces recognition process using Haar cascades and eigenface methods," in Proceedings of 2018 6th International Conference on Multimedia Computing and Systems (ICMCS), Rabat, Morocco, 2018, pp. 1-5. https://doi.org/10.1109/ICMCS.2018.8525935
  20. J. Guo, J. Deng, A. Lattas, and S. Zafeiriou, "Sample and computation redistribution for efficient face detection," 2021 [Online]. Available: https://arxiv.org/abs/2105.04714.
  21. N. Guisande, M. P. di Nunzio, N. Martinez, O. A. Rosso, and F. Montani, "Chaotic dynamics of the Henon map and neuronal input-output: a comparison with neurophysiological data," Chaos: An Interdisciplinary Journal of Nonlinear Science, vol. 33, no. 4, article no. 043111, 2023. https://doi.org/10.1063/5.0142773