• Version
• Download 13
• File Size 476.18 KB
• File Count 1
• Create Date 29 July 2025
• Last Updated 29 July 2025

Two Factor Worm Detection Based on Signature & Anomaly

PINNAMRAJU T S PRIYA, BHUPATHI HARI TEJA

Assistant professor, Head of the Department, 2 MCA Final Semester, Master of Computer Applications, Sanketika Vidya Parishad Engineering College, Vishakhapatnam,

Andhra Pradesh, India.

Abstract

WormShield AI is an innovative final-year project leveraging artificial intelligence and dual-factor analysis for advanced internet worm detection. It integrates both signature-based detection and anomaly-based detection techniques to safeguard systems against malicious infiltration with enhanced accuracy and speed.

The system utilizes packet signature analysis, honeypot logging, and NetFlow inspection to identify known threats, while machine learning models—such as Random Forest, Decision Tree, and Bayesian Networks—are trained on historical traffic data to recognize abnormal behavior patterns. These models enable real-time traffic classification into NORMAL or ABNORMAL categories.

Complementing the detection engine, WormShield AI introduces a Two-Factor Detection Framework, ensuring each request is evaluated through both static signature matching and dynamic anomaly detection.[5]This layered defense mechanism offers robust protection against worms that attempt to corrupt files, extract sensitive data, or establish backdoors into user systems.

The platform features a streamlined user interface for monitoring traffic insights, analyzing alerts, and updating detection models. WormShield AI is designed to assist cybersecurity teams in early threat identification, support secure enterprise networks, and offer intelligent, AI-driven defenses against evolving cyber threats.

Index Terms: Cybersecurity, Artificial Intelligence, Internet Worms, Signature Detection, Anomaly Detection, Honeypot, NetFlow, Machine Learning.