SeLCM: An Efficient and Robust Malware Detection Model

In today’s era, all aspects of life are digitized and therefore prone to digitized attacks. These days there are various criminal activities that are intended to harm the user in one or the other way. Most of them are based on the internet, computers, or specifically computational resources. These may include phishing, cyber fraud, social engineering, cyberstalking, DDoS attacks, malware, and many more. Some of these crimes target networks or devices, and one of them is malware. In this paper, we have discussed different types of malwares, their comparison, and various malware detection techniques. We have also considered static, dynamic, and hybrid malware analysis in later sections of the paper. Finally, we have proposed a naïve model for malware detection. This research's implications for malware detection with hybrid approaches are discussed.