IoT-based Android Malware Detection Using Graph Neural Network With Adversarial Defense

TL;DR

This paper presents a graph neural network approach for Android malware detection in IoT, achieving high accuracy, and introduces a GAN-based attack to evaluate and improve the model's robustness against adversarial manipulations.

Contribution

It introduces a GNN-based malware detection method combining API graphs with permission and intent features, and proposes a GAN-based attack to enhance model robustness.

Findings

Achieved over 98% accuracy on benchmark datasets.

Demonstrated vulnerability of GNN models to adversarial graph attacks.

Retraining with adversarial samples improves detection robustness.

Abstract

Since the Internet of Things (IoT) is widely adopted using Android applications, detecting malicious Android apps is essential. In recent years, Android graph-based deep learning research has proposed many approaches to extract relationships from applications as graphs to generate graph embeddings. First, we demonstrate the effectiveness of graph-based classification using a Graph Neural Network (GNN)-based classifier to generate API graph embeddings. The graph embeddings are combined with Permission and Intent features to train multiple machine learning and deep learning models for Android malware detection. The proposed classification approach achieves an accuracy of 98.33 percent on the CICMaldroid dataset and 98.68 percent on the Drebin dataset. However, graph-based deep learning models are vulnerable, as attackers can add fake relationships to evade detection by the classifier. Second, we propose a Generative Adversarial Network (GAN)-based attack algorithm named VGAE-MalGAN targeting graph-based GNN Android malware classifiers. The VGAE-MalGAN generator produces adversarial malware API graphs, while the VGAE-MalGAN substitute detector attempts to mimic the target detector. Experimental results show that VGAE-MalGAN can significantly reduce the detection rate of GNN-based malware classifiers. Although the model initially fails to detect adversarial malware, retraining with generated adversarial samples improves robustness and helps mitigate adversarial attacks.