Machine Learning-Based Reversible Chaotic Masking Method for User Privacy Protection in CCTV Environment
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In modern society, user privacy is emerging as an important issue as closed-circuit television (CCTV) systemsincrease rapidly in various public and private spaces. If CCTV cameras monitor sensitive areas or personalspaces, 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 riskof data leakage by hackers or illegal accessors. This paper presents an innovative approach to “machine learningbased reversible chaotic masking method for user privacy protection in CCTV environment.” The proposedmethod was developed to protect an individual's identity within CCTV images while maintaining the usefulnessof 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 CCTVframe. This model is designed to identify individuals accurately and robustly by leveraging state-of-the-artobject 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 andidentifiable characteristics. Above all, the generated mask can be reversibly applied and removed, allowingauthorized users to access the original unmasking image.
Abstract
In modern society, user privacy is emerging as an important issue as closed-circuit television (CCTV) systemsincrease rapidly in various public and private spaces. If CCTV cameras monitor sensitive areas or personalspaces, 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 riskof data leakage by hackers or illegal accessors. This paper presents an innovative approach to “machine learningbased reversible chaotic masking method for user privacy protection in CCTV environment.” The proposedmethod was developed to protect an individual's identity within CCTV images while maintaining the usefulnessof 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 CCTVframe. This model is designed to identify individuals accurately and robustly by leveraging state-of-the-artobject 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 andidentifiable characteristics. Above all, the generated mask can be reversibly applied and removed, allowingauthorized users to access the original unmasking image.
참고문헌 (21)
- Sheeraz Muhammad, "Effective Security Monitoring using Efficient SIEM Architecture", Human-centric Computing and Information Sciences, 13, pp.1~18 (2023), 한국컴퓨터산업협회[DOI]
- Ding Wei, "Role of Sensors Based on Machine Learning Health Monitoring in Athletes' Wearable Heart Rate Monitoring", Human-centric Computing and Information Sciences, 13, pp.1~16 (2023), 한국컴퓨터산업협회[DOI]
- T. Jaichuen, "BLUR & TRACK: real-time face detection with immediate blurring and efficient tracking", Proceedings of 2023 20th International Joint Conference on Computer Science and Software Engineering (JCSSE), pp.167~172 (2023)
- 권병욱, "CCTV-Based Multi-Factor Authentication System", JIPS(Journal of Information Processing Systems), 15(4), pp.904~919 (2019), 한국정보처리학회[DOI]
- Donghyeok Lee, "Blockchain based privacy preserving multimedia intelligent video surveillance using secure Merkle tree", Multimedia Tools and Applications, 80(26-27), pp.34517~34534 (2020), Springer Science and Business Media LLC[DOI]
- S. Prange, "Priview: exploring visualisations to support users’ privacy awareness", Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems, pp.1~18 (2021)
- "Building a privacy-preserving smart camera system" (2022)[URL]
- Endah Kristiani, "Binary and Multi-Class Assessment of Face Mask Classification on Edge AI Using CNN and Transfer Learning", Human-centric Computing and Information Sciences, 12(0), pp.729~744 (2022), KIPS-CSWRG[DOI]
- E. Jasinskaite, "Combining deep privacy with an attribute-driven generative adversarial network to preserve gender and age in de-identified CCTV footage", M. S., pp.2021
- Zhixuan Zhong, "Delving deep into pixelized face recovery and defense", Neurocomputing, 513, pp.233~246 (2022), Elsevier BV[DOI]
- Jizhe Zhou, "Personal Privacy Protection via Irrelevant Faces Tracking and Pixelation in Video Live Streaming", IEEE Transactions on Information Forensics and Security, 16, pp.1088~1103 (2021), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- J. Zhou, "Privacy-sensitive objects pixelation for live video streaming", Proceedings of the 28th ACM International Conference on Multimedia, pp.3025~3033 (2020)
- Lei Li, "Replayed Video Attack Detection Based on Motion Blur Analysis", IEEE Transactions on Information Forensics and Security, 14(9), pp.2246~2261 (2019), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Xiao Hu, "Surveillance video face recognition with single sample per person based on 3D modeling and blurring", Neurocomputing, 235, pp.46~58 (2017), Elsevier BV[DOI]
- T. Rakhimzhanova, "Face and facial landmark detection for event-based imaging", M.S., School of Engineering and Digital Sciences, pp.2023
- Sung-su Jang, "L-GAN: landmark-based generative adversarial network for efficient face de-identification", The Journal of Supercomputing, 79(7), pp.7132~7159 (2022), Springer Science and Business Media LLC[DOI]
- J. Lin, "Accurate and Fast mask recognition based on multiple color areas detection and face landmarks locating", Proceedings of 2022 IEEE 22nd International Conference on Communication Technology (ICCT), pp.1463~1467 (2022)
- "BlazeFace: sub-millisecond neural face detection on mobile GPUs" (2019)[URL]
- T. Mantoro, "Multi-faces recognition process using Haar cascades and eigenface methods", Proceedings of 2018 6th International Conference on Multimedia Computing and Systems (ICMCS), pp.1~5 (2018)
- "Sample and computation redistribution for efficient face detection" (2021)[URL]
- Natalí Guisande, "Chaotic dynamics of the Hénon map and neuronal input–output: A comparison with neurophysiological data", Chaos: An Interdisciplinary Journal of Nonlinear Science, 33(4) (2023), AIP Publishing[DOI]