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{196044,
        author = {V. Sai Siri Chandana and S. Bindu Bhavana and V. Sri Charan and P. Poojitha and K. Sharmila},
        title = {CyberSheild: Security awareness web application},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {1789-1796},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=196044},
        abstract = {The exponential growth of cyber threats has created an urgent need for accessible, intelligent, and engaging cybersecurity awareness platforms that cater to users across diverse age groups and technical backgrounds. This paper presents CyberShield, a full-stack AI-driven cybersecurity awareness web application that integrates eight cohesive modules under a unified, responsive interface. The platform combines a structured Cyber Crime Report Centre powered by large language model (LLM) forensic analysis, a conversational AI chatbot capable of generating personalised learning roadmaps, a 26-signal hybrid phishing URL detection engine paired with a real-time Chrome browser extension, a threat news aggregator, a curated job listings hub, an AI-powered myth-busting verification engine, a dynamic events management board, and an age-stratified gamified quiz system with live leaderboards.
Experimental evaluation demonstrates that the URL phishing detection algorithm achieves 93.4% classification accuracy (F1 = 0.934) on a combined PhishTank-OpenPhish evaluation corpus. A pilot user study involving 90 participants across three age cohorts recorded statistically significant knowledge-retention gains exceeding 31 percentage points (p < 0.001, Cohen's d > 1.8) following two weeks of platform engagement. System benchmarking recorded a mean API response latency of 138 ms under 200 concurrent simulated users, confirming production-grade viability. The platform is implemented using React 18, Node.js/Express, MongoDB, Groq LLM API, and Chrome Manifest V3.},
        keywords = {Cybersecurity Awareness, Phishing Detection, AI Chatbot, Gamified Learning, Browser Extension, LLM Forensics, Myth Verification, Age-Adaptive Quiz, MERN Stack.},
        month = {April},
        }