{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T05:07:23Z","timestamp":1778821643689,"version":"3.51.4"},"reference-count":28,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T00:00:00Z","timestamp":1777507200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computation"],"abstract":"<jats:p>Modern user authentication systems increasingly need user and device-behavior-aware adaptive mechanisms to detect evolving threats beyond the traditional authentication framework of static credential verification. This paper proposes a hybrid multi-model framework for personalized user-level anomaly detection using a data-driven Hybrid Anomaly Score (HAS). The primary contribution lies in deriving the HAS using the joint integration of three adaptive attributes: dynamically computed per-user deviation thresholds conditioned on individual behavioral history, profile-age-aware baseline weights reflecting user cohort maturity, and criticality-scaled aggregation with the security impact of each detection methodology. The framework is evaluated on a large-scale real-world dataset and demonstrates strong detection performance, while achieving low inference latency suitable for real-time enterprise deployment. The ablation analysis of the framework confirms that dynamic weighting and personalized threshold substantially improve detection stability and convergence with an effective and deployable solution for large-scale authentication environments.<\/jats:p>","DOI":"10.3390\/computation14050102","type":"journal-article","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T14:35:53Z","timestamp":1777559753000},"page":"102","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Hybrid Multi-Model Framework for Personalized User-Level Anomaly Detection with Data-Driven Threshold Optimization"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8859-0601","authenticated-orcid":false,"given":"Amit","family":"Kumar","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Indian Institute of Information Technology, Sonepat 131021, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wakar","family":"Ahmad","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Indian Institute of Information Technology, Sonepat 131021, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Om","family":"Pal","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Delhi, Delhi 110007, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5177-4004","authenticated-orcid":false,"family":"Sunil","sequence":"additional","affiliation":[{"name":"Department of University Polytechnic, Jamia Millia Islamia, New Delhi 110025, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,30]]},"reference":[{"key":"ref_1","unstructured":"(2020). Zero Trust Architecture (Standard No. SP 800-207)."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Atlam, H.F., Azad, M.A., Alassafi, M.O., Alshdadi, A.A., and Alenezi, A. (2020). Risk-Based Access Control Model: A Systematic Literature Review. Future Internet, 12.","DOI":"10.3390\/fi12060103"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/j.inffus.2020.08.021","article-title":"Behavioral Biometrics and Continuous User Authentication on Mobile Devices: A Survey","volume":"66","author":"Stylios","year":"2021","journal-title":"Inf. Fusion"},{"key":"ref_4","first-page":"12","article-title":"Dynamic Risk-Based Authentication Using AI Scoring Models in Healthcare Applications","volume":"4","author":"Khan","year":"2025","journal-title":"J. Cloud Comput."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Ji, I.H., Lee, J.H., Kang, M.J., Park, W.J., Jeon, S.H., and Seo, J.T. (2024). Artificial Intelligence-Based Anomaly Detection Technology over Encrypted Traffic: A Systematic Review. Sensors, 24.","DOI":"10.3390\/s24030898"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Wairagade, A., and Ranjan, S. (2025, January 24\u201325). User Behavior Analysis for Cyber Threat Detection: A Comparative Study of Machine Learning Algorithms. Proceedings of the 2025 13th International Symposium on Digital Forensics and Security (ISDFS), Boston, MA, USA.","DOI":"10.1109\/ISDFS65363.2025.11011949"},{"key":"ref_7","first-page":"45","article-title":"Adaptive Anomaly Detection in Database Transactions: Bridging Security Gaps with Reinforcement Learning","volume":"5","author":"Sharma","year":"2025","journal-title":"Eur. J. Artif. Intell. Mach. Learn."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"61129","DOI":"10.1109\/ACCESS.2023.3286376","article-title":"RLAuth: A risk-based authentication system using reinforcement learning","volume":"11","author":"Picard","year":"2023","journal-title":"IEEE Access"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Islam, M.S., Rakha, M.S., Pourmajidi, W., Sivaloganathan, J., Steinbacher, J., and Miranskyy, A. (May, January 27). Anomaly Detection in Large-Scale Cloud Systems: An Industry Case and Dataset. Proceedings of the 2025 IEEE\/ACM 47th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP), Ottawa, ON, Canada.","DOI":"10.1109\/ICSE-SEIP66354.2025.00039"},{"key":"ref_10","first-page":"34","article-title":"Zero Trust Security: An Enterprise Guide","volume":"22","author":"Shamir","year":"2024","journal-title":"IEEE Secur. Priv."},{"key":"ref_11","first-page":"45","article-title":"Authentication and Access Control: Emerging Trends in Credential Abuse Detection","volume":"28","author":"Sandhu","year":"2024","journal-title":"IEEE Internet Comput."},{"key":"ref_12","first-page":"22","article-title":"Adaptive trust authentication protocol for risk-based security: Leveraging behavior analysis and trust scores in IAM systems","volume":"25","author":"Premsai","year":"2024","journal-title":"Int. J. Comput. Appl."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Megahed, A.A., Arnous, M.F., Elmoataz, Y., Moussa, A., Haitham, S., and Hany, M. (2024, January 19\u201321). Enhanced security through intelligent risk-based authentication: Leveraging big data and machine learning for real-time threat mitigation. Proceedings of the 6th Novel Intelligent and Leading Emerging Sciences Conference (NILES), Giza, Egypt.","DOI":"10.1109\/NILES63360.2024.10753250"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Iskhakov, A.Y., Mamchenko, M.V., and Khripunov, S.P. (2023, January 27\u201331). Enhanced user authentication algorithm based on behavioral analytics in web-based cyberphysical systems. Proceedings of the International Russian Smart Industry Conference (SmartIndustryCon), Sochi, Russia.","DOI":"10.1109\/SmartIndustryCon57312.2023.10110791"},{"key":"ref_15","first-page":"210","article-title":"AI-Driven Frameworks for Anomaly Detection: Comparative Analysis of Machine Learning and Deep Learning Models","volume":"5","author":"Patel","year":"2025","journal-title":"Int. J. Adv. Sci. Tech. Res."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Bonneau, J., Herley, C., van Oorschot, P.C., and Stajano, F. (2012). The Quest to Replace Passwords: A Framework for Comparative Evaluation of Web Authentication Schemes. Proceedings of the IEEE Symposium on Security and Privacy, IEEE.","DOI":"10.1109\/SP.2012.44"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Wiefling, S., Lo Iacono, L., and D\u00fcrmuth, M. (2020). Is This Really You? An Empirical Study on Risk-Based Authentication Applied in the Wild. arXiv.","DOI":"10.1007\/978-3-030-22312-0_10"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1007\/s10462-024-10893-1","article-title":"Deep learning-based authentication for insider threat detection in critical infrastructure","volume":"57","author":"Budzys","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"ref_19","first-page":"100572","article-title":"A comprehensive study of auto-encoders for anomaly detection: Efficiency and trade-offs","volume":"17","author":"Neloy","year":"2024","journal-title":"Mach. Learn. Appl."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Akram, S.V., Joshi, S.K., and Deorari, R. (2022, January 18\u201319). Web application based authentication system. Proceedings of the International Interdisciplinary Humanitarian Conference for Sustainability (IIHC), Bengaluru, India.","DOI":"10.1109\/IIHC55949.2022.10059984"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"136","DOI":"10.32996\/jcsts.2024.6.3.12","article-title":"The future of identity and access management: Leveraging AI for enhanced security and efficiency","volume":"3","author":"Vitla","year":"2024","journal-title":"J. Comput. Sci. Technol. Stud."},{"key":"ref_22","unstructured":"Sakurada, M., Yairi, T., Zhou, C., and Paffenroth, R.C. (2017, January 13\u201317). Anomaly Detection with Robust Deep Autoencoders. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Halifax, NS, Canada."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1690","DOI":"10.1016\/j.eswa.2013.08.066","article-title":"A Novel Hybrid Intrusion Detection Method Integrating Anomaly Detection with Misuse Detection","volume":"41","author":"Kim","year":"2014","journal-title":"Expert Syst. Appl."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Liu, F.T., Ting, K.M., and Zhou, Z.-H. (2012). Isolation-Based Anomaly Detection. ACM Trans. Knowl. Discov. Data, 6.","DOI":"10.1145\/2133360.2133363"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1186\/s13677-024-00712-x","article-title":"Explainable AI-Based Hybrid Ensemble Model for Intrusion Detection","volume":"13","author":"Ahmed","year":"2024","journal-title":"J. Cloud Comput."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"e555","DOI":"10.1002\/itl2.555","article-title":"Beyond passwords: A multi-factor authentication approach for robust digital security","volume":"8","author":"Simha","year":"2025","journal-title":"Internet Technol. Lett."},{"key":"ref_27","unstructured":"Amft, S., H\u00f6ltervennhoff, S., Huaman, N., Krause, A., Simko, L., Acar, Y., and Fahl, S. (2023, January 26\u201330). \u201cWe\u2019ve Disabled MFA for You\u201d: An Evaluation of the Security and Usability of Multi-Factor Authentication Recovery Deployments. Proceedings of the ACM SIGSAC Conference on Computer and Communications Security (CCS \u201923), Copenhagen, Denmark."},{"key":"ref_28","first-page":"567","article-title":"Securing Anomaly Detection for Process-Based Time Series","volume":"198","author":"Smith","year":"2024","journal-title":"Nucl. Sci. Eng."}],"container-title":["Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-3197\/14\/5\/102\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T04:12:09Z","timestamp":1778818329000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-3197\/14\/5\/102"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,30]]},"references-count":28,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["computation14050102"],"URL":"https:\/\/doi.org\/10.3390\/computation14050102","relation":{},"ISSN":["2079-3197"],"issn-type":[{"value":"2079-3197","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,30]]}}}