Cyber Chronicles: Tracking Behavior Patterns for Detecting Threats in Large Networks
Senthilnathan Ramasubbu, Senthil Kumar Thangavel, Gurusamy Jeyakumar · 2024
One of the primary challenges in cybersecurity is that even one un-detected, appropriately unanalyzed malicious security event can hide the attack vectors of a potential hacker. It is essential to detect the data breach at the earliest stage to reduce the impact on the business. The malicious actor’s activities will have higher visibility during the initial attacks to compromises or exploitation at the beginning of the attack cycle. After the initial compromise, the attacker studies the environment and establishes the persistence and covert channel communication. At this successive phase of the attack cycle, the attacker camouflages with the production data flow, access, and noises in the network and application logs. It is essential to detect the attacks during the reconnaissance and initial attacks and should not miss any malicious activities. Most of our security tools focus on reducing false positives; however, reducing false negatives is critical to cyber security. Hence, this paper is focused on suitable deep learning to reduce the False Negatives (FNs) with minimal Type II error to detect the attacks well in advance.