Detecting crypto-ransomware in IoT networks based on
energy consumption footprint

Azmoodeh, A; Dehghantanha, A; Conti, M; Raymond Choo, K-K

Abstract

An Internet of Things (IoT) architecture generally consists of a wide range of Internet-connected devices or things such as Android devices, and devices that have more computational capabilities (e.g., storage capacities) are likely to be targeted by ransomware authors.
In this paper, we present a machine learning based approach to detect ransomware attacks by monitoring power consumption of Android devices. Specifically, our proposed method monitors the energy consumption patterns of different processes to classify ransomware
from non-malicious applications. We then demonstrate that our proposed approach out-performs K-Nearest Neighbors, Neural Networks, Support Vector Machine and Random
Forest, in terms of accuracy rate, recall rate, precision rate and F-measure.

• Journal Article Type: Article
• Acceptance Date: Jul 28, 2017
• Online Publication Date: Aug 23, 2017
• Publication Date: Aug 23, 2017
• Deposit Date: Aug 1, 2017
• Publicly Available Date: Aug 24, 2017
• Journal: Journal of Ambient Intelligence and Humanized Computing
• Print ISSN: 1868-5137
• Electronic ISSN: 1868-5145
• Publisher: Springer Verlag
• Volume: 9
• Issue: 4
• Pages: 1141-1152
• DOI: https://doi.org/10.1007/s12652-017-0558-5
• Publisher URL: http://dx.doi.org/10.1007/s12652-017-0558-5
• Related Public URLs: https://link.springer.com/journal/12652
• Additional Information: Funders : European Council International Incoming Fellowship; Projects : Privacy4Forensic; Grant Number: FP7-PEOPLE-2013-IIF