شناسایی چهره افراد بر اساس مدل معنایی برای موبایل بانک
محورهای موضوعی : مهندسی کامپیوتر و فناوری اطلاعات
لیلی نصرتی
1
,
امیرمسعود بیدگلی
2
,
حمید حاج سید جوادی
3
1 - دانشکده فنی مهندسی دانشگاه آزاد اسلامی واحد تهران شمال
2 - Department of Computer Engineering, Tehran North Branch,Islamic Azad University, Tehran, Iran
3 - استاد دانشگاه شاهد
کلید واژه: احراز هویت چهره, بانکداری همراه, مدل معنایی, الگوریتم ژنتیک, درخت تصمیم.,
چکیده مقاله :
چکیده: در این مقاله، یک پروتکل احراز هویت جدید برای بانکداری آنلاین بر اساس مدل معنایی ویژگی¬های استخراج شده از تصویر افراد معرفی شده است. رویکرد پیشنهادی با استفاده از تلفن¬های همراه هوشمند برای تصویربرداری دیجیتال برای مشتریان ارائه شده است. در این روش از خوشه‌بندی فازی برای دسته‌بندی ویژگی‌های تصاویر افراد مختلف استفاده شده است و با اعمال آن‌ها در روش‌های مختلف یادگیری ماشین، ترکیب روش‌های طبقه‌بندی یادگیری ماشینی برای بهبود عملکرد و افزایش قدرت در برابر حملات مختلف ارائه شده است. همچنین به منظور کاهش پیچیدگی طراحی ماشین برای کارهای عملیاتی، از روش کاهش ویژگی¬های استخراج شده از تصاویر چهره افراد به کمک الگوریتم ژنتیک و در قسمت آخر برای تصمیم¬گیری جهت احراز هویت فرد انتخاب شده، از سیستم منطق فازی بر اساس بالاترین دقت شناسایی فرد مورد نظر استفاده شده است. با استفاده از یک مجموعه داده عمومی، نتایج تجربی نشان داد که روش مبتنی بر الگوریتم ژنتیک بهترین انتخاب ویژگی برای ایجاد یک روش احراز هویت ضمنی برای محیط تلفن هوشمند است. نتیجه محاسبات دقت حدود 80/99% را با استفاده از تنها 30 ویژگی از 77 ویژگی برای احراز هویت کاربران نشان داد که بیانگر نیاز به منابع کمتر تلفن همراه است.
In this paper, a new authentication protocol for online banking based on the semantic model of features extracted from people's image is introduced. The proposed approach is presented using smart mobile phones for online digital imaging for customers. In this work, a fuzzy clustering has been used to categorize the characteristics of the images of different people and by applying them to different machine learning methods, a combined technique of machine learning classification methods has been presented to improve performance and increases strength against various attacks. Also to reduce the complexity of machine design for operational tasks, the technique of reducing features extracted from face images with the help of genetic algorithm has been used. In the last part, in order to make a decision for authentication selected by machine learning systems, a fuzzy logic system is presented based on the highest accuracy of identifying the desired person. Using a public dataset, the experimental results showed that the genetic algorithm-based technique is the best feature selection to create an implicit authentication method for the smartphone environment. The results showed an accuracy of about 99.80% using only 30 features out of 77 to authenticate users. At the same time, the results showed that the proposed method has a lower error rate compared to the related work.
[1] Smith-Creasey M, Albalooshi FA, & Rajarajan M (2018) Continuous face authentication scheme for mobile devices with tracking and liveness detection. Microprocess Microsyst 63:147-157.
[2] Jafri R & Arabnia HR (2009) A survey of face recognition techniques. J Inf Process Syst 5:41-68.
[3] Mohan J, & Rajesh R (2021) Enhancing home security through visual cryptography. Microprocess Microsyst 80:103355.
[4] Adesuyi F A, Oluwafemi O, Oludare AI & Rick A (2013) Secure authentication for mobile banking using facial recognition.
[5] Stragapede G et al. (2022) Mobile behavioral biometrics for passive authentication. Pattern Recognit Lett 157: 35-41.
[6] Saxena N & Varshney D (2021) Smart Home Security Solutions using Facial Authentication and Speaker Recognition through Artificial Neural Networks. International Journal of Cognitive Computing in Engineering 2:154-164.
[7] Zeroual A, Amroune M, Derdour M & Bentahar A (2021) Lightweight deep learning model to secure authentication in Mobile Cloud Computing. J. King Saud Univ. - Comput Inf Sci.
[8] Pérez JC, Alfarra M, Thabet A, Arbeláez P & Ghanem B (2022) Towards Assessing and Characterizing the Semantic Robustness of Face Recognition. arXiv preprint arXiv:2202.04978.
[9] Gong D, Zhu K, Li Z & Qiao Y (2013) in 2013 IEEE International Conference on Information and Automation (ICIA). 1369-1374 (IEEE).
[10] El-Soud MWA, Gaber T, AlFayez F & Eltoukhy MM (2021) Implicit authentication method for smartphone users based on rank aggregation and random forest. Alex Eng J 60:273-283.
[11] Shu Y et al. in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 11916-11925.
[12] Samangouei P, Patel VM & Chellappa R (2017) Facial attributes for active authentication on mobile devices. Image Vis Comput 58:181-192.
[13] Yanakova E, Ishkova T, Belyaev A, Koldaev V & Kolobanova M (2019) in 2019 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus). 1848-1851 (IEEE).
[14] Gudi A (2015) Recognizing semantic features in faces using deep learning. arXiv preprint arXiv:1512.00743.
[15] Almudhahka NY, Nixon MS & Hare JS (2017) in 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017). 180-185 (IEEE).
[16] de Castro D C & Nowozin S: in Proceedings of the European Conference on Computer Vision (ECCV). 745-761.
[17] Choi HS & Cho YH (2019) Analysis of Security Problems of Deep Learning Technology. Journal of the Korea Convergence Society 10: 9-16.
[18] Najafabadi MM et al. (2015) Deep learning applications and challenges in big data analytics. J Big Data 2:1-21.
[19] Kim Th: in International Conference on Information Security and Assurance. 138-148 (Springer).
[20] Sujatha K et al. in Proceedings of International Conference on Sustainable Computing in Science, Technology and Management (SUSCOM), Amity University Rajasthan, Jaipur-India.
[21] Redla SS, Mallik B & Mangalampalli VK (2020) in 2020 2nd International Conference on Innovative Mechanisms for Industry Applications (ICIMIA). 223-229 (IEEE).
[22] Ruspini EH (1969) A new approach to clustering. Information and control 15:22-32.
[23] Bezdek JC (1980) A convergence theorem for the fuzzy ISODATA clustering algorithms. IEEE Trans Pattern Anal Mach Intell 1-8.
[24] Li MJ, Ng MK, Cheung Ym. & Huang JZ (2008) Agglomerative fuzzy k-means clustering algorithm with selection of number of clusters. IEEE Trans Knowl Data Eng 20:1519-1534.
[25] Naruei I & Keynia F (2021) Wild horse optimizer: A new meta-heuristic algorithm for solving engineering optimization problems. Eng Comput 1-32.
[26] Wu YL, Tang CY, Hor MK & Wu PF (2011) Feature selection using genetic algorithm and cluster validation. Expert Syst Appl 38:2727-2732.
[27] Venkatesh B & Anuradha J (2019) A review of feature selection and its methods. Cybern Inf Technol 19:3-26.
[28] Malhotra R, Singh N & Singh Y (2011) Genetic algorithms: Concepts, design for optimization of process controllers. Comput Sci Inf Syst 4:39.
[29] Pei M, Goodman E & Punch W. in Proceedings of the 1st International Symposium on Intelligent Data Engineering and Learning, IDEAL. 371-384.
[30] Suardani LGP, Bhaskara IMA & Sudarma M (2018) Optimization of Feature Selection Using Genetic Algorithm with Naïve Bayes Classification for Home Improvement Recipients. Int J Eng Emerging Technol 3:66-70.
[31] Huszár VD & Adhikarla VK (2021) Live spoofing detection for automatic human activity recognition applications. Sensors 21:7339.
[32] Milborrow S, Morkel J & Nicolls F (2010) The MUCT landmarked face database. Pattern recognition association of South Africa 201.
[33] Cherifi F, Hemery B, Giot R, Pasquet M & Rosenberger C (2010) in Behavioral biometrics for human identification: Intelligent applications 57-74 (IGI Global, 2010).
[34] Maglogiannis I, Iliadis L, Macintyre J & Cortez P (2022) Artificial Intelligence Applications and Innovations: 18th IFIP WG 12.5 International Conference, AIAI 2022, Hersonissos, Crete, Greece, June 17–20, 2022, Proceedings, Part II. Vol. 647 (Springer Nature, 2022).
[35] Eberz S, Rasmussen KB, Lenders V & Martinovic I (2017) in Proceedings of the 2017 ACM on Asia conference on computer and communications security. 386-399.
[36] Buriro A, Crispo B, Frari FD, Klardie J & Wrona K: in International conference on passwords. 45-61 (Springer).
[37] Kumar R, Phoha VV & Raina R (2016) Authenticating users through their arm movement patterns. arXiv preprint arXiv:1603.02211.
[38] Shrestha B, Mohamed M & Saxena N (2016) Walk-unlock: Zero-interaction authentication protected with multi-modal gait biometrics. arXiv preprint arXiv:1605.00766.
[39] Ehatisham-ul-Haq M et al (2017) Authentication of smartphone users based on activity recognition and mobile sensing. Sensors 17:2043.
[40] Li G & Bours P (2018) in 2018 21st International Conference on Information Fusion (FUSION). 2091-2097 (IEEE).
[41] Buriro A, Crispo B & Conti M (2019) AnswerAuth: A bimodal behavioral biometric-based user authentication scheme for smartphones. J Inf Secur Appl 44:89-103.
[42] Volaka HC, Alptekin G, Basar OE, Isbilen M & Incel OD (2019) Towards continuous authentication on mobile phones using deep learning models. Procedia Comput Sci 155:177-184.
[43] Lamiche I, Bin G, Jing Y, Yu Z & Hadid A (2019) A continuous smartphone authentication method based on gait patterns and keystroke dynamics. J Ambient Intell Humaniz Comput 10: 4417-4430.
[1] [44] Abuhamad M, Abuhmed T, Mohaisen D & Nyang D (2020) AUToSen: Deep-learning-based implicit continuous authentication using smartphone sensors. IEEE Internet Things J 7:5008-5020.Object Management Group. Unified Modeling Language: Superstructure, Version 2.0, ptc/03-07-06, July 2003, http://www.omg.org/cgi-bin/doc?ptc/2003-08-02.
