Detection of Malware Using Deep Learning
Shadman Newaz, Hasan Md Imran, Xingya Liu · 2021 IEEE 4th International Conference on Computing, Power and Communication Technologies (GUCON) · 2021
In the progressive world, cyber-crime has become a big threat for every person, companies and national security system. With the rapid evolution and noteworthy successes in wide range of applications, Deep Learning (DL) has been applied in many safety-oriented environments for protecting applications. DL techniques have been used for foremost challenges in cybersecurity problems like intrusion detection, classification and detection of malware, spam detection and phishing detection. However, DL also can have misprediction due to internal/external malicious properties, it may produce complications in our real life. To avoid these drawbacks, this paper describes a new algorithm for the detection of malicious cyber-attack using DL and to minimize misprediction of DL techniques. Furthermore, Extensive research experiments are carried out in order to isolate the adversaries adequately. The result of our proposed algorithm displays that it can achieve a higher defensive rate with minimal amount of misprediction level.