Machine Learning-Based Detection of Forensic Artifacts and Anomalies in Tails OS

Cybercrime poses significant challenges in the modern, interconnected world, making it increasingly difficult for law enforcement agencies to track and identify cyber criminals. Privacy-focused operating systems, such as Tails OS, have become a tool for cybercriminals to maintain anonymity and conceal their digital traces. This research explores developing and implementing machine learning models to automate the detection of forensic artifacts and anomalous user behavior within disk images and network traffic associated with Tails OS. By leveraging tools such as FTK Imager, Wireshark, and Python for data extraction and processing, the study provides a detailed methodology for data collection, preprocessing, feature engineering, and model training and helps law enforcement investigate and collect digital evidence. The approach aims to strengthen forensic investigations and improve the identification of potential evidence in privacy-centric environments.