Venkata Nagaraju Thatha
| Srihari Varma Mantena | Chandra Sekhar Reddy LingaReddy | Phanikanth Chintamaneni | Revathy Pulugu | Venkata Subbaiah Desanamukula*
OPEN ACCESS
The proliferation of face images, alongside their widespread dissemination and easy accessibility through social media, underscores a pressing challenge to personal identification information protection. Conversely, advancements in identity-agnostic computer vision technologies offer valuable benefits, necessitating cautious utilization of face images to safeguard individual privacy. 'Face de-identification', or 'face anonymization', refers to the process of altering an original face image to a near-identical one that obscures the subject's actual identity. Existing de-identification strategies, despite considerable efforts, often fall short in photo-realism or fail to strike an optimal balance between privacy and utility. This study proposes an approach for generating de-identified facial images using instances, addressing the potential privacy breaches and identity exposure associated with facial features. The proposed system involves a two-stage training process. Initially, a federated learning framework is suggested, enabling knowledge amalgamation through the mutual exchange of model parameters among clients during federated training, devoid of data sharing. Subsequently, sensitive information is secured using an enhanced version of the Diffie-Hellman algorithm coupled with a genetic algorithm. In the event of data loss or corruption, an optimized genetic algorithm (OGA) is employed to successfully restore the data, thereby offering protection against potential insider threats in federated learning. The decryption process is then executed as if the user had initiated the request. Experimental results demonstrate that the proposed federated learning approach delivers performance equivalent to centralized learning, thereby validating the practicality and effectiveness of the suggested architecture. Specifically, a model of the federated learning-deep convolutional neural network (FL-DCNN) achieved an accuracy of 95.2%, precision and F1-score of 95%, recall of 96%, and a final specificity of 96.80%.
face images, federated learning, genetic algorithm, extended version of Diffie-Hellman procedure, deep learning, data leakage, privacy
The ubiquitous presence of mobile phones in contemporary society facilitates effortless capture of spontaneous self-portraits. Particularly, the swift evolution of media and network technologies has amplified the accessibility of a vast array of photographs [1]. Nevertheless, burgeoning image retrieval and face verification models have enabled indexing and analysis of data potentially sensitive to individual privacy with an unprecedented degree of precision [2]. Consequently, the scale of private information inadvertently divulged among image sources publicly accessible, knowingly or unknowingly, is often grossly underestimated [3]. The unguarded facial images, combined with state-of-the-art computer vision technology, present myriad, and potentially catastrophic, opportunities for misuse [4].
The increasing application of facial recognition in sectors such as banking and other financial transactions amplifies the significance of this technology, alongside the use of biometrics. Progress in microelectronics and vision systems have mainstreamed biometrics as a lucrative industry [5]. Within the biometrics sphere, facial recognition holds paramount importance. Modern information is juxtaposed with human characteristics using biometrics. An efficient method is employed to extract and apply facial features, with minor modifications to the original algorithm model to further enhance its accuracy [6]. Computerized facial recognition harbors substantial potential in areas such as criminal identification, surveillance, and identity verification. The face in the input image is initially isolated using face detection processes, followed by the image processing phase which cleans the face for easy recognition [7].
As the avenues for individual identification worldwide continue to multiply daily, facial recognition technology has emerged as an indispensable necessity in the present era [8]. Over the past two decades, research in face recognition has thrived owing to its extensive applicability in domains such as image analysis and comprehension. Face recognition finds utility in a diverse array of fields, from computer science to medicine [9, 10]. Facial recognition is user-friendly, compact, and can swiftly gain ubiquity. Security, entertainment, attendance tracking, and even financial transactions represent potential applications for facial recognition technology [11]. Despite the robust performance of current facial recognition systems in laboratory conditions, their real-world application in surveillance systems is significantly hampered by challenges related to image quality, background clutter, variations in illumination, and changes in facial and expression posture.
Typically, face recognition systems encompass three stages: image preprocessing, feature extraction, and recognition classification [12]. Geometric features include facial characteristics that can be extracted such as lips, nose, eyebrows, etc. The detected and processed face is matched with a database of known faces to ascertain the individual's identity. The surveillance system necessitates human supervision. However, human monitoring presents limitations in terms of reliability, scalability, and individual identification [13]. Facial occlusions, including beards and accessories (glasses, hats, and masks), complicate the evaluation of face recognition systems in a realistic environment. Another critical factor to consider is the abundance of terminologies used to denote a similar concept: Macro and micro terminologies find their place on an individual's face, and effective recognition becomes challenging due to the diversity of such expressions [14, 15]. An ideal face recognition system would cater to a large number of users with minimal photographs, while remaining resilient to changes in lighting, emotions, postures, and occlusions.
The primary contributions of this paper can be summarized as follows:
The remainder of this paper is organized as follows: Section 2 provides an overview of the relevant literature. The methodology is delineated in Section 3, while Section 4 discusses the results. Section 5 constitutes the conclusion of the paper.
[1] Naseri, R.A.S., Kurnaz, A., Farhan, H.M. (2023). Optimized face detector-based intelligent face mask detection model in IoT using deep learning approach. Applied Soft Computing, 134, 109933. https://doi.org/10.1016/j.asoc.2022.109933
[2] Alzu’bi, A., Albalas, F., Al-Hadhrami, T., Younis, L.B., Bashayreh, A. (2021). Masked face recognition using deep learning: A review. Electronics, 10(21): 2666. https://doi.org/10.3390/electronics10212666
[3] Kumar, K.K., Kasiviswanadham, Y., Indira, D.V.S.N.V., Bhargavi, C.V. (2023). Criminal face identification system using deep learning algorithm multi-task cascade neural network (MTCNN). Materials Today: Proceedings, 80: 2406-2410. https://doi.org/10.1016/j.matpr.2021.06.373
[4] Macherla, H., Kotapati, G., Sunitha, M.T., Chittipireddy, K.R., Attuluri, B., Vatambeti, R. (2023). Deep learning framework-based chaotic hunger games search optimization algorithm for prediction of air quality index. Ingénierie des Systèmes d’Information, 28(2): 433-441. https://doi.org/10.18280/isi.280219
[5] Wang, M., Deng, W. (2021). Deep face recognition: A survey. Neurocomputing, 429: 215-244. https://doi.org/10.1016/j.neucom.2020.10.081
[6] Mamieva, D., Abdusalomov, A.B., Mukhiddinov, M., Whangbo, T.K. (2023). Improved face detection method via learning small faces on hard images based on a deep learning approach. Sensors, 23(1): 502. https://doi.org/10.3390/s23010502
[7] Tabassum, F., Islam, M. I., Khan, R. T., & Amin, M. R. (2022). Human face recognition with combination of DWT and machine learning. Journal of King Saud University-Computer and Information Sciences, 34(3): 546-556. https://doi.org/10.1016/j.jksuci.2020.02.002
[8] Chen, W., Huang, H., Peng, S., Zhou, C., Zhang, C. (2021). YOLO-face: A real-time face detector. The Visual Computer, 37: 805-813. https://doi.org/10.1007/s00371-020-01831-7
[9] Boyd, A., Tinsley, P., Bowyer, K.W., Czajka, A. (2023). Cyborg: Blending human saliency into the loss improves deep learning-based synthetic face detection. In 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA, pp. 6097-6106. https://doi.org/10.1109/WACV56688.2023.00605
[10] Li, X., Lai, S., Qian, X. (2021). DBCFace: Towards pure convolutional neural network face detection. IEEE Transactions on Circuits and Systems for Video Technology, 32(4): 1792-1804. https://doi.org/10.1109/TCSVT.2021.3082635
[11] Ali, W., Tian, W., Din, S.U., Iradukunda, D., Khan, A.A. (2021). Classical and modern face recognition approaches: A complete review. Multimedia Tools and Applications, 80: 4825-4880. https://doi.org/10.1007/s11042-020-09850-1
[12] Veesam, V.S., Ravichandran, S., Babu, G.R.M. (2022). Deep neural networks for automatic facial expression recognition. Revue d'Intelligence Artificielle, 36(5): 809-814. https://doi.org/10.18280/ria.360520
[13] Rajeshkumar, G., Braveen, M., Venkatesh, R., Shermila, P.J., Prabu, B.G., Veerasamy, B., Bharathi, B., Jeyam, A. (2023). Smart office automation via faster R-CNN based face recognition and Internet of Things. Measurement: Sensors, 27: 100719. https://doi.org/10.1016/j.measen.2023.100719
[14] Sethi, S., Kathuria, M., Kaushik, T. (2021). Face mask detection using deep learning: An approach to reduce risk of Coronavirus spread. Journal of Biomedical Informatics, 120: 103848. https://doi.org/10.1016/j.jbi.2021.103848
[15] Hariri, W. (2022). Efficient masked face recognition method during the COVID-19 pandemic. Signal, Image and Video Processing, 16(3): 605-612. https://doi.org/10.1007/s11760-021-02050-w
[16] Kulkarni, S., Shrivastava, P., Bodineni, P.L., Ambhore, N., Choudhari, D., Chaudhari, D. (2023). Attendance Monitoring system using face recognition. Scandinavian Journal of Information Systems, 35(1): 115-123.
[17] Dosi, M., Agarwal, S., Chaudhary, J., Manchanda, S., Balutia, K., Bhagwatkar, K., Vatsa, M., Singh, R. (2023). Seg-DGDNet: Segmentation based disguise guided dropout network for low resolution face recognition. IEEE Journal of Selected Topics in Signal Processing, 1-13. https://doi.org/10.1109/JSTSP.2023.3288398
[18] Zennayi, Y., Benaissa, S., Derrouz, H., Guennoun, Z. (2023). Unauthorized access detection system to the equipments in a room based on the persons identification by face recognition. Engineering Applications of Artificial Intelligence, 124: 106637. https://doi.org/10.1016/j.engappai.2023.106637
[19] Contardo, P., Sernani, P., Tomassini, S., Falcionelli, N., Martarelli, M., Castellini, P., Dragoni, A.F. (2023). FRMDB: Face recognition using multiple points of view. Sensors, 23(4): 1939. https://doi.org/10.3390/s23041939
[20] Lakshmi, N., Arakeri, M.P. (2023). Sketch-based face recognition using deep neural network for criminal investigation. In: Smys, S., Tavares, J.M.R.S., Shi, F. (eds) Computational Vision and Bio-Inspired Computing. Advances in Intelligent Systems and Computing, vol 1439. Springer, Singapore. https://doi.org/10.1007/978-981-19-9819-5_33
[21] Lv, X., Su, M.X., Wang, Z.K. (2021). Application of face recognition method under deep learning algorithm in embedded systems. Microprocessors and Microsystems, 104034, https://doi.org/10.1016/j.micpro.2021.104034
[22] Vijayalakshmi, S., Maheswari, J.U., Jananiyie, K. (2023). Face detection and recognition using machine learning techniques. Journal of Innovative Image Processing, 4(4): 316-327. https://doi.org/10.36548/jiip.2022.4.008
[23] Yang, Q., Liu, Y., Chen, T., Tong, Y. (2019). Federated machine learning: Concept and applications. ACM Transactions on Intelligent Systems and Technology (TIST), 10(2): 1-19. https://doi.org/10.1145/3298981
[24] Cheng, K., Fan, T., Jin, Y., Liu, Y., Chen, T., Papadopoulos, D., Yang, Q. (2021). SecureBoost: A lossless federated learning framework. IEEE Intelligent Systems, 36(6): 87-98. https://doi.org/10.1109/MIS.2021.3082561
[25] Li, Q., Wen, Z., He, B. (2020). Practical federated gradient boosting decision trees. In Proceedings of the AAAI Conference on Artificial Intelligence, 34(4): 4642-4649. https://doi.org/10.1609/aaai.v34i04.5895
[26] Yu, H., Liu, Z., Liu, Y., Chen, T., Cong, M., Weng, X., Niyato, D., Yang, Q. (2020). A sustainable incentive scheme for federated learning. IEEE Intelligent Systems, 35(4): 58-69. https://doi.org/10.1109/MIS.2020.2987774
[27] Karras, T., Aila, T., Laine, S., Lehtinen, J. (2017). Progressive growing of GANs for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196. https://doi.org/10.48550/arXiv.1710.10196
[28] Liu, Z., Luo, P., Wang, X., Tang, X. (2015). Deep learning face attributes in the wild. In 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, pp. 3730-3738. https://doi.org/10.1109/ICCV.2015.425
[29] Chen, J.C., Patel, V.M., Chellappa, R. (2016). Unconstrained face verification using deep CNN features. In 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Placid, NY, USA, pp. 1-9. https://doi.org/10.1109/WACV.2016.7477557
[30] McMahan, B., Moore, E., Ramage, D., Hampson, S., y Arcas, B.A. (2017). Communication-efficient learning of deep networks from decentralized data. In Artificial Intelligence and Statistics, pp. 1273-1282.
[31] Hirsch, P.D. (2019). Task scheduling using improved weighted round Robin techniques. U.S. Patent 10,324,755.
[32] Zaharia, M., Chowdhury, M., Franklin, M.J., Shenker, S., Stoica, I. (2010). Spark: Cluster computing with working sets. In 2nd USENIX Workshop on Hot Topics in Cloud Computing (HotCloud 10), pp. 1-7.