Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{197765,
        author = {Ruchi Chavhan and Rumaisha Ansari and Anjali Deogade and Prajakta Agashe and Omkar Dudhbure},
        title = {AI Cyber Threat Detection and Secure Authentication System: An Integrated Machine Learning Approach},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {7570-7574},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=197765},
        abstract = {The exponential growth of cyber threats has rendered traditional security mechanisms inadequate for protecting sensitive user data against sophisticated attacks. This paper presents a comprehensive AI-Based Cyber Threat Detection and Secure Authentication System that leverages Machine Learning to identify suspicious login activities and protect against multiple attack vectors including brute-force attacks, phishing, malware distribution, and network intrusions. The proposed system employs the Random Forest algorithm to analyze login patterns based on three key parameters: password length, number of login attempts, and time of access. Upon detecting three consecutive failed login attempts, the system automatically implements account blocking and generates real-time security alerts with confidence scores. Additional features include heuristic-based phishing link detection, malware file scanning using pattern matching, network IP monitoring against malicious databases, and comprehensive logging for audit trails. The backend is implemented using Python Flask, MongoDB for data persistence, and scikit-learn for the machine learning model. Experimental results demonstrate that the system successfully detects brute-force attack patterns with 85-90% accuracy, providing an additional security layer beyond traditional authentication methods.},
        keywords = {Cyber Threat Detection, Machine Learning, Random Forest, Phishing Detection, Malware Scanner, Flask, MongoDB, Authentication System, Brute-Force Prevention},
        month = {April},
        }