AI-Based Smart Honeypot System for Cyber Attack Intelligence

Abstract

The rapid growth of digital technologies has increased the number of cyberattacks targeting online systems and user data. Traditional security methods such as firewalls and intrusion detection systems are often unable to handle advanced and evolving threats effectively. To address this issue, this paper proposes an AI-Based Smart Honeypot System for Cyberattack Intelligence that combines machine learning, behavioral analysis, and deception techniques for detecting malicious activities in real time. The proposed system monitors user activities such as login attempts, typing behavior, session timing, and interaction patterns to identify suspicious behavior. A machine learning model is used to classify users as legitimate or malicious based on these behavioral features. If suspicious activity is detected, the user is redirected to a fake environment that appears similar to a real system, allowing the collection of attacker information without exposing sensitive data. The system was tested using simulated normal and malicious user activities, and the results showed improved detection accuracy with reduced false positives. The proposed approach not only improves cybersecurity protection but also helps in gathering valuable cyber threat intelligence for future analysis. Overall, the system provides a practical and scalable solution for modern cybersecurity challenges. Keywords: cybersecurity; artificial intelligence; machine learning; Anomaly detection; Intrusion Detection System; Smart Honeypot; Behavioral Analysis; Deception Technology; Threat Intelligence; Attack Detection