Enhancing IoT Malware Detection through Adaptive Model Parallelism and Resource Optimization

TL;DR

This paper presents a resource-aware, adaptive malware detection method for IoT devices that dynamically distributes detection tasks across devices, significantly improving speed while maintaining high accuracy.

Contribution

It introduces a novel resource and workload-aware model parallelism approach for IoT malware detection, optimizing resource use and privacy.

Findings

Achieves 9.8x speedup over on-device detection

Maintains 96.7% malware detection accuracy

Dynamically allocates detection tasks based on resource availability

Abstract

The widespread integration of IoT devices has greatly improved connectivity and computational capabilities, facilitating seamless communication across networks. Despite their global deployment, IoT devices are frequently targeted for security breaches due to inherent vulnerabilities. Among these threats, malware poses a significant risk to IoT devices. The lack of built-in security features and limited resources present challenges for implementing effective malware detection techniques on IoT devices. Moreover, existing methods assume access to all device resources for malware detection, which is often not feasible for IoT devices deployed in critical real-world scenarios. To overcome this challenge, this study introduces a novel approach to malware detection tailored for IoT devices, leveraging resource and workload awareness inspired by model parallelism. Initially, the device assesses available resources for malware detection using a lightweight regression model. Based on resource availability, ongoing workload, and communication costs, the malware detection task is dynamically allocated either on-device or offloaded to neighboring IoT nodes with sufficient resources. To uphold data integrity and user privacy, instead of transferring the entire malware detection task, the classifier is divided and distributed across multiple nodes, then integrated at the parent node for detection. Experimental results demonstrate that this proposed technique achieves a significant speedup of 9.8 x compared to on-device inference, while maintaining a high malware detection accuracy of 96.7%.