HIDROID: Prototyping a Behavioral Host-Based Intrusion Detection and Prevention System for Android

Jose Ribeiro, Firooz B. Saghezchi, Georgios Mantas, Jonathan Rodriguez, Raed A. Abd-Alhameed

Research output: Contribution to journalArticlepeer-review

32 Downloads (Pure)

Abstract

Previous research efforts on developing an Intrusion Detection and Prevention Systems (IDPS) for Android mobile devices rely mostly on centralized data collection and processing on a cloud server. However, this trend is characterized by two major limitations. First, it requires a continuous connection between monitored devices and the server, which might be infeasible, due to mobile network's outage or partial coverage. Second, it increases the risk of sensitive information leakage and the violation of user's privacy. To help alleviate these problems, in this paper, we develop a novel Host-based IDPS for Android (HIDROID), which runs completely on a mobile device, with a minimal computation burden. It collects data in run-time, by periodically sampling features reflecting the utilization of scarce resources on a mobile device (e.g. CPU, memory, battery, bandwidth, etc.). The detection engine exploits statistical and machine learning algorithms to build a data-driven model for the benign behavior. Any observation failing to match this model triggers an alert, and the preventive agent takes proper countermeasure(s) to minimize the risk. HIDROID requires no malicious data for training or tuning, which makes it handy for day-to-day usage. Experimental test results, on a real-life device, show that HIDROID is well able to learn and discriminate normal from malicious behavior, with very promising accuracy of up to 0.9, while maintaining false positive rate by 0.03.
Original languageEnglish
Article number8970345
Pages (from-to)23154-23168
Number of pages15
JournalIEEE Access
Volume8
DOIs
Publication statusPublished - 27 Jan 2020

Keywords

  • Android
  • anomaly detection
  • behavior analysis
  • intrusion detection and prevention system (IDPS)
  • machine learning
  • malware detection
  • prototype development
  • security and privacy

Fingerprint

Dive into the research topics of 'HIDROID: Prototyping a Behavioral Host-Based Intrusion Detection and Prevention System for Android'. Together they form a unique fingerprint.

Cite this