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{205742,
        author = {Mohan Chavhan and Aditya Dhat and Aarya Dhope and Sucheta Navale},
        title = {THREAT DETECTION AND ALERT SYSTEM FOR IOT NETWORKS(CYBERSHIELD)},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {8319-8326},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=205742},
        abstract = {CyberShield is an advanced threat detection and alert system designed to enhance the security of Internet of Things (IoT) networks by identifying and analyzing malicious activities in real-time. With the rapid growth of IoT devices, networks have become increasingly vulnerable to sophisticated cyber-attacks such as Denial of Service (DoS), ARP spoofing, port scanning, and data interception [1], [6]. The system aims to address these security challenges by providing a hybrid intrusion detection mechanism that combines machine learning-based anomaly detection with signature-based real-time packet analysis. CyberShield offers a robust and intelligent framework that continuously monitors network traffic, detects abnormal patterns, and generates instant alerts to the system administrator. The machine learning component utilizes a Random Forest classifier trained specifically on the BoT-IoT dataset to identify unknown and zero-day attacks, achieving a 100.00% accuracy metric with perfect 1.00 precision and recall scores on a test split of 733,705 packets. Simultaneously, the signature-based engine employs real-time packet sniffing techniques using Python’s Scapy library [9] to instantly detect 7 distinct attack vectors including ICMP/TCP/UDP floods and stealth XMAS/FIN scans without memory exhaustion or packet dropping. The system incorporates libraries such as Scikit-learn, Pandas, Streamlit, and Rich, ensuring efficient processing. The platform provides a unified monitoring dashboard that seamlessly integrates both asynchronous AI predictions and synchronous signature alerts, enabling administrators to visualize threats, analyze network behavior, and respond proactively.},
        keywords = {CyberShield, Intrusion Detection System (IDS), IoT Security, Machine Learning, Random Forest, Packet Sniffing, Scapy, Network Security, Anomaly Detection, Cyber Attacks, Real-Time Monitoring.},
        month = {June},
        }