USER BEHAVIOR ANALYSIS USING MACHINE LEARNING FOR ENHANCED SECURITY WITH 2FA/MFA AUTHENTICATION ( RISK DETECTION AND MITIGATION )

Registration ID: IJNRD_306910

Published ID: IJNRD2505325

DOI: Click Here to Get

Talha Hoda , Manish Raj , Sharanaabasppa Halle , Shrikant Bhor , Nilesh Suryawanshi

Security, User Behaviour Analytics, Machine Learning, Adaptive Authentication, Fraud Detection, Anomaly Detection, Multi-Factor Authentication (MFA), Risk-Based Authentication, Long Short-Term Memory (LSTM), Isolation Forest, Behavioural Profiling, Artificial Intelligence in Authentication

With the rapid evolution of cybersecurity threats, conventional authentication mechanisms such as password-based access control and static multi-factor authentication (MFA) are proving increasingly vulnerable to sophisticated attacks, including credential stuffing, phishing, and session hijacking. As cybercriminals develop advanced tactics to bypass authentication barriers, traditional security models often fail to balance strong fraud prevention with a seamless user experience. This paper presents an adaptive anomaly detection system designed to strengthen authentication security by leveraging a hybrid approach using Long Short-Term Memory (LSTM) networks and Isolation Forest. The proposed model dynamically learns from historical authentication behavior, assessing risk levels in real time to determine whether a user should receive a JSON Web Token (JWT) for session continuation or be prompted for Time-Based One-Time Password (TOTP) validation via MFA enforcement. By integrating behavior-aware fraud detection models, the system successfully minimizes unnecessary authentication prompts while ensuring robust security enforcement for high-risk login attempts. The framework is implemented using Fast API for real-time authentication workflows, offering low-latency processing for instant fraud detection and security enforcement decisions. Ethical considerations regarding user privacy and bias in anomaly detection are discussed, ensuring responsible AI practices in authentication security models. Scalability challenges in high-traffic environments are examined, along with strategies to optimize performance in cloud-based deployment scenarios. Furthermore, reinforcement learning-based improvements are proposed to dynamically adjust anomaly thresholds and security measures based on evolving user authentication patterns. Additionally, this paper explores the comparative evaluation of anomaly detection techniques, highlighting the advantages of the LSTM-Isolation Forest hybrid model over conventional approaches such as Autoencoders, Statistical Methods, and Decision Trees. Experimental results demonstrate high detection precision, reduced security fatigue, and improved fraud prevention accuracy, reinforcing the effectiveness of machine learning-powered adaptive authentication in real-world security frameworks. The findings and implementation strategies outlined in this paper serve as a foundation for the next generation of authentication mechanisms, ensuring continuous security adaptation, fraud mitigation, and dynamic authentication workflows tailored to evolving cyber threats.

Published Paper   E-Certificate

Talha Hoda, Manish Raj, Sharanaabasppa Halle, Shrikant Bhor, & Nilesh Suryawanshi (May-2025). USER BEHAVIOR ANALYSIS USING MACHINE LEARNING FOR ENHANCED SECURITY WITH 2FA/MFA AUTHENTICATION ( RISK DETECTION AND MITIGATION ). INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT, 10(5), d327-d337. https://ijnrd.org/papers/IJNRD2505325.pdf

Volume 10 Issue 5, May-2025

Pages : d327-d337

Paper Reg. ID: IJNRD_306910

Published Paper Id: IJNRD2505325

Downloads: 000122016

Research Area: Science and Technology

Country: pune, Maharashtra, India

Published Paper PDF: https://ijnrd.org/papers/IJNRD2505325.pdf

Published Paper URL: https://ijnrd.org/viewpaperforall?paper=IJNRD2505325

Journal Name: INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT(IJNRD)

ISSN: 2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar | ESTD YEAR: 2016

An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator

Publisher: IJNRD (IJ Publication) Janvi Wave | IJNRD.ORG | IJNRD.COM | IJPUB.ORG

This work is licensed under a Creative Commons Attribution 4.0 International License and The Open Definition

Call For Paper - Volume 10 | Issue 10 | October 2025

IJNRD is a Scholarly Open Access, Peer-reviewed, and Refereed Journal with a High Impact Factor of 8.76 (calculated by Google Scholar & Semantic Scholar | AI-Powered Research Tool). It is a Multidisciplinary, Monthly, Low-Cost Journal that follows UGC CARE 2025 Peer-Reviewed Journal Policy norms, Scopus journal standards, and Transparent Peer Review practices to ensure quality and credibility. IJNRD provides indexing in all major databases & metadata repositories, a citation generator, and Digital Object Identifier (DOI) for every published article with full open-access visibility.

The INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT (IJNRD) aims to advance applied, theoretical, and experimental research across diverse fields. Its goal is to promote global scientific information exchange among researchers, developers, engineers, academicians, and practitioners. IJNRD serves as a platform where educators and professionals can share research evidence, models of best practice, and innovative ideas, contributing to academic growth and industry relevance.

Indexing Coverage includes Google Scholar, SSRN, ResearcherID-Publons, Semantic Scholar (AI-Powered Research Tool), Microsoft Academic, Academia.edu, arXiv.org, ResearchGate, CiteSeerX, ResearcherID (Thomson Reuters), Mendeley, DocStoc, ISSUU, Scribd, and many more recognized academic repositories.

How to submit the paper?

By Our website

Click Here to Submit Paper Online

By Mail

Send your paper to editor@ijnrd.org

Important Dates for Current issue

Paper Submission Open For: October 2025

Current Issue: Volume 10 | Issue 10 | October 2025

Impact Factor: 8.76

Last Date for Paper Submission: Till 31-Oct-2025

Notification of Review Result: Within 1-2 Days after Submitting paper.

Publication of Paper: Within 01-02 Days after Submititng documents.

Frequency: Monthly (12 issue Annually).

Journal Type: IJNRD is an International Peer-reviewed, Refereed, and Open Access Journal with Transparent Peer Review as per the new UGC CARE 2025 guidelines, offering low-cost multidisciplinary publication with Crossref DOI and global indexing.

Subject Category: Research Area

Call for Paper: More Details