Qualitative Analyze of the Cyber Crime Challenges and Legal Frameworks Using Machine Learning

Cyber-attacks are increasingly becoming one of the most pressing global challenges. These threats can be mitigated by utilizing real-time data to identify attacks and their sources. Such data can be sourced from systems that have been compromised, particularly those within forensic units dealing with cyber incidents. It has been observed that many cyber-attacks are driven by social, financial, economic, or cultural conflicts. These attacks aim to destabilize vital networks, such as government, military, or other critical infrastructure systems. A cyber attack typically targets diverse systems that provide essential services, combining tactics with the objectives of the attacker. This research explores the application of machine learning (ML) algorithms-specifically Random Forest and K-Nearest Neighbor (KNN)-to assess their effectiveness in detecting cyber-attacks. The study compares the performance of these models under different conditions and identifies the one that offers the best resilience for various data indices. Machine learning enables cybersecurity systems to detect patterns in real time, which can help prevent malicious activities and allow security teams to take proactive measures against potential threats.