• Divyanshi Chaudhary
• Abhinav Pandey
• Arantha Shreya Gogoi
• Tanu Rajput
• Mangala L

This research paper presents an intelligent hybrid framework that uses forensic log analysis along with machine learning-based user behavior modeling for the detection of insider threats. This paper explores how parsing of Windows event logs and forensic timeline construction, along with using machine learning models for behavioral anomaly detection based on mouse movements, typing speed, click rhythms, keystroke latency, mouse-movement trajectories, and session-time patterns, can be used for the detection of insider threats. Isolation Forest, Random Forest, SVM, and LSTM are some models used to detect deviations from normal user behavior. This framework not only produces an objective anomaly score but also provides forensic evidence to establish accountability. This is done by correlating event timelines from Windows logs with behavioral patterns derived from the ML model. The paper shows how integration of AI with cyber forensics can help in the detection of insider threats.

Insider Threat Detection, User Behaviour Analytics (UBA),Digital Forensics, Machine Learning, Anomaly Detection, Behavioural Biometrics, Credential Misuse, Log Analysis, Isolation Forest, Random Forest, Support Vector Machine (SVM), Long Short-Term Memory (LSTM), Event Correlation, Cybersecurity, Windows Event Logs.

"Enhanced Insider Threat Detection Using Machine Learning and Hayabusa-based User Behaviour Analytics", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 11, page no.e346-e352, November-2025, Available :http://www.jetir.org/papers/JETIR2511443.pdf

"Enhanced Insider Threat Detection Using Machine Learning and Hayabusa-based User Behaviour Analytics", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 11, page no. ppe346-e352, November-2025, Available at : http://www.jetir.org/papers/JETIR2511443.pdf