RoboMal: Malware Detection for Robot Network Systems

TL;DR

RoboMal introduces a static malware detection framework specifically designed for robotic systems, utilizing a new dataset and machine learning models to identify malware in binary executables before execution.

Contribution

The paper presents RoboMal, a novel static malware detection framework for robots, along with a new dataset, outperforming existing models in accuracy and precision.

Findings

RoboMal achieves 85% accuracy in malware detection.

LSTM-based RoboMal outperforms CNN, GRU, and ANN models.

The dataset supports further research in robotic malware security.

Abstract

Robot systems are increasingly integrating into numerous avenues of modern life. From cleaning houses to providing guidance and emotional support, robots now work directly with humans. Due to their far-reaching applications and progressively complex architecture, they are being targeted by adversarial attacks such as sensor-actuator attacks, data spoofing, malware, and network intrusion. Therefore, security for robotic systems has become crucial. In this paper, we address the underserved area of malware detection in robotic software. Since robots work in close proximity to humans, often with direct interactions, malware could have life-threatening impacts. Hence, we propose the RoboMal framework of static malware detection on binary executables to detect malware before it gets a chance to execute. Additionally, we address the great paucity of data in this space by providing the RoboMal dataset comprising controller executables of a small-scale autonomous car. The performance of the framework is compared against widely used supervised learning models: GRU, CNN, and ANN. Notably, the LSTM-based RoboMal model outperforms the other models with an accuracy of 85% and precision of 87% in 10-fold cross-validation, hence proving the effectiveness of the proposed framework.