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{194751,
        author = {Kelvin Patel and Umme Amarah and Pasalapudi Siddhi and Puppala Vijayaraghavulu},
        title = {ML model to Refine CAPTCHA},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {4775-4781},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=194751},
        abstract = {The rise of automated bots poses significant threats to websites, including fraudulent transactions, data scraping, spam, and DoS/DDoS attacks. Traditional CAPTCHA-based solutions, while effective in the past, introduce usability issues such as poor accessibility, increased user friction, and vulnerability to AI-based solvers. As bots become more sophisticated, CAPTCHA systems are becoming less reliable, necessitating a more efficient and user-friendly approach to bot detection.
This paper presents a passive AI/ML-driven bot detection system that operates in the background, eliminating the need for intrusive CAPTCHA challenges. The proposed system analyzes environmental parameters such as browser metadata, device fingerprints, user interaction behavior (mouse movements, keystroke dynamics, scrolling patterns). A machine learning model processes this data in real-time, classifying users as bots or humans without disrupting their experience.
The key advantage of this approach is its seamless integration with web platforms, ensuring high accuracy and minimal user interaction. The system continuously improves through adaptive learning, enhancing detection efficiency against evolving bot threats. Additionally, it maintains strong privacy compliance, encrypting data and adhering to global data protection regulations such as GDPR and CCPA.
Our results demonstrate that this AI-powered system significantly outperforms CAPTCHA-based methods, providing a scalable, privacy-conscious, and user-friendly solution for modern bot detection.},
        keywords = {Bot Detection, CAPTCHA Replacement, Machine Learning, AI Security, Passive Authentication, Behavioral Biometrics, Fraud Prevention, Web Security, Cybersecurity, Data Privacy.},
        month = {March},
        }