Ripple20 Vulnerabilities Detection using a Featureless Deep Learning Model
Sarah Bin Hulayyil, Shancang Li · 2023
Inherent vulnerabilities create new security risks and challenges that leave Internet of Things (IoT) systems open to cyber attacks. Featureless deep learning shows immense potential in vulnerability detection without relying on explicit feature engineering in the IoT. Featureless deep learning models provide a low-cost and low memory time-series analysis of network traffic. This paper proposes a featureless DL procedure in a 1D CNN model to carry out Ripple20 detection. The experimental results demonstrate the effectiveness of the proposed solution, as it is beneficial for decreasing the time spent on feature engineering. Specifically, this proposed featureless model achieved 99% accuracy and an F1score of 99% in less time than traditional methods.