Enhancing Enterprise Network Security: Comparing Machine-Level and Process-Level Analysis for Dynamic Malware Detection
This addresses the problem of isolating malicious processes instead of whole machines for enterprise network security, though it is incremental by improving detection in realistic scenarios with background applications.
The study tackled dynamic malware detection by comparing machine-level and process-level analysis, finding that background applications reduce state-of-the-art accuracy by 20.12% on average, and their proposed process-level RNN model achieved a 0.049 increase in detection rate with a false-positive rate below 0.1.
Analysing malware is important to understand how malicious software works and to develop appropriate detection and prevention methods. Dynamic analysis can overcome evasion techniques commonly used to bypass static analysis and provide insights into malware runtime activities. Much research on dynamic analysis focused on investigating machine-level information (e.g., CPU, memory, network usage) to identify whether a machine is running malicious activities. A malicious machine does not necessarily mean all running processes on the machine are also malicious. If we can isolate the malicious process instead of isolating the whole machine, we could kill the malicious process, and the machine can keep doing its job. Another challenge dynamic malware detection research faces is that the samples are executed in one machine without any background applications running. It is unrealistic as a computer typically runs many benign (background) applications when a malware incident happens. Our experiment with machine-level data shows that the existence of background applications decreases previous state-of-the-art accuracy by about 20.12% on average. We also proposed a process-level Recurrent Neural Network (RNN)-based detection model. Our proposed model performs better than the machine-level detection model; 0.049 increase in detection rate and a false-positive rate below 0.1.