Robust Intelligent Malware Detection using De...

Robust Intelligent Malware Detection using Deep Learning

Author Name : S. K. Shammi, I. Pravalika, R. Lakshmi Prasanna, V. Guru Charan Gupta, P. Venkata Rakesh

Malicious software poses a significant security threat in the digital age, with an exponential growth in attacks. Current detection solutions use static and dynamic analysis, which are time-consuming and ineffective. Recent malwares use evasive techniques to quickly change their behaviour and generate large numbers of malwares. Machine learning algorithms (MLAs) are being employed to conduct effective malware analysis, but their performance is biased with training data. This work evaluates classical MLAs and deep learning architectures for malware detection, classification, and categorization using both public and private datasets. A novel image processing technique with optimal parameters is proposed for MLAs and deep learning architectures. A comprehensive experimental evaluation shows that deep learning architectures outperform classical MLAs. This work proposes an effective visual detection of malware using a scalable and hybrid deep learning framework for real-time deployments.

Keywords: Malicious software, exponential growth, deep learning, malwares, effective.