A Deep Learning–Based Malware and Intrusion Detection Framework
Pavitra Kadiyala, Kakelli Anil Kumar · 2022
Cyberattacks have increased a lot in the past few years. There are numerous cyberattacks, such as ransomware, DOS, DDoS, Phishing, BOTS, etc. These attacks have serious consequences, steal and damage confidential data. The usage of web applications has expanded and resulted in more malware attacks. Subsequently, it is essential to prevent emerging malware and attacks. An Intrusion Detection System (IDS) is a highly crucial part of network security IDS monitors the network and data traffic. Attacks are taken place on the IDS. A few examinations have been done in this field, yet profound and comprehensive work is still ongoing. Machine learning and deep learning models are helpful in the cyber security domain. This paper introduces a web application for IDS and malware attack detection using machine learning (logistic regression and random forest classifier) and deep learning (artificial neural network) models. To examine the blends of the vast majority of components that help detect the attacks, we trained our proposed model using existing datasets to predict the security attack.