An Intelligent Malware Detection and Classification System Using Apps-to-Images Transformations and Convolutional Neural Networks | IEEE Conference Publication | IEEE Xplore

An Intelligent Malware Detection and Classification System Using Apps-to-Images Transformations and Convolutional Neural Networks


Abstract:

With the proliferation of Mobile Internet, handheld devices are facing continuous threats from apps that contain malicious intents. These malicious apps, or malware, have...Show More

Abstract:

With the proliferation of Mobile Internet, handheld devices are facing continuous threats from apps that contain malicious intents. These malicious apps, or malware, have the capability of dynamically changing their intended code as they spread. Moreover, the diversity and volume of their variants severely undermine the effectiveness of traditional defenses, which typically use signature-based techniques, and make them unable to detect the previously unknown malware. However, the variants of malware families share typical behavioral patterns reflecting their origin and purpose. The behavioral patterns, obtained either statically or dynamically, can be exploited to detect and classify unknown malware into their known families using machine learning techniques. In this paper, we propose a new approach for detecting and analyzing a malware. Mainly focused on android apps, our approach adopts the two following steps: (1) performs a transformation of an APK file into a lightweight RGB image using a predefined dictionary and intelligent mapping, and (2) trains a convolutional neural network on the obtained images for the purpose of signature detection and malware family classification. The results obtained using the Androzoo dataset show that our system classifies both legacy and new malware apps with high accuracy, low false-negative rate (FNR), and low false-positive rate (FPR).
Date of Conference: 12-14 October 2020
Date Added to IEEE Xplore: 13 November 2020
ISBN Information:

ISSN Information:

Conference Location: Thessaloniki, Greece

References

References is not available for this document.