Improving Robustness in IoT Malware Detection through Execution Order Analysis

Abstract

The rapid expansion of the Internet of Things (IoT) has significantly increased the prevalence of malware targeting IoT devices. Although machine learning models offer promising solutions for automatic malware detection, they are increasingly vulnerable to adversarial attacks. These attacks exploit the model’s feedback loop to iteratively refine malware, producing adversarial samples that evade detection. As such, enhancing the robustness of these models is of paramount importance. Our research introduces a novel approach to bolster malware detection by retaining additional semantic information within the execution order analysis of malware programs. The method significantly improves the resilience of detection models against adversarial samples and implements two adversarial attack methods to rigorously test our model’s robustness by generating authentic adversarial examples for validation. We highlight the critical impact of preserving semantic integrity in malware detection and present a solution to counteract the growing threat of adversarial attacks in IoT environments.