IIoT Deep Malware Threat Hunting: From Adversarial Example Detection to Adversarial Scenario Detection

Bardia Esmaeili, Amin Azmoodeh, Ali Dehghantanha, Behrouz Zolfaghari, Hadis Karimipour, Mohammad Hammoudeh

Research output: Contribution to journalArticlepeer-review

Abstract

Protecting widely-used deep classifiers against black-box adversarial attacks is a recent research challenge in many security-related areas, including malware classification. This class of attacks relies on optimizing a sequence of highly similar queries to bypass given classifiers. In this paper, we leverage this property and propose a history-based method named, Stateful Query Analysis (SQA), which analyzes sequences of queries received by a malware classifier to detect black-box adversarial attacks on an Industrial Internet of Things (IIoT).In the SQA pipeline, there are two components, namely the similarity encoder and the classifier, both based on Convolutional Neural Networks (CNNs). Unlike state-of-the-art methods, which aim to identify individual adversarial examples, tracking the history of queries allows our method to identify adversarial scenarios and abort attacks before their completion. We optimize SQA using different combinations of hyperparameters on an ARM-based IIoT malware dataset, widely adopted for malware threat hunting in Industry 4.0.

Original languageEnglish
JournalIEEE Transactions on Industrial Informatics
DOIs
Publication statusAccepted/In press - 2022

Keywords

  • Adversarial Detection
  • Convolutional Neural Networks
  • Feature extraction
  • Gray-scale
  • Industrial Internet of Things
  • Industrial Internet of Things
  • Industry 40
  • Informatics
  • Malware
  • Malware Classification
  • Malware Threat Hunting
  • Mathematical models
  • Training

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Information Systems
  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'IIoT Deep Malware Threat Hunting: From Adversarial Example Detection to Adversarial Scenario Detection'. Together they form a unique fingerprint.

Cite this