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{193219,
        author = {Sakshi Bansal and Khushi Gupta and Tanushka Kashyap and Swayan Nain},
        title = {LeakAlert - Insider Threat & Anomaly Detection System},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {9},
        pages = {4598-4603},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=193219},
        abstract = {Organizations nowadays are very dependent on internal computer systems and there is a need to keep track of how users behave and what they are doing in the systems. Despite the fact that the majority of security tools have been developed to prevent external attacks, a significant number of security challenges are caused by insiders who have already gained access to the systems either purposefully or through some unintentional practices. In this project, a basic system of insider-monitoring was established to track the attempts of logging in, information about the device, IP location, file access pattern and other suspicious patterns in real time. The system computes a risk score based on failed logins, access to restricted files, new device or unusual location logins among others. The system is not based on labeled data but rather a combination of rule-based checks with unsupervised machine-learning models to identify abnormal behavior. An Isolation Forest model is used to examine the patterns of logins, device changes, change of location, and file-access activity to determine the abnormal behavior of the user. A dynamic risk score is created by combining the model output with the real-time security rules, which enhances the accuracy of the detection without proving to be an unrealistic concept when implemented in real-world enterprise settings.},
        keywords = {Anomaly Detection, cybersecurity, insider threat, Isolation Forest, machine learning.},
        month = {February},
        }