Label Noise Detection in IoT Security based on Decision Tree and Active Learning

Classification is an essential and important task in Machine Learning (ML). The existence of label noise in training datasets can negatively impact the performance of supervised classification. Due to the growing interest in the data-centric AI that aims at improving the quality of training data without enhancing the complexity of models, there have been a variety of research works to tackle the label noise problem. However, few works have investigated this problem in the IoT network intrusion detection domain. This paper addresses the issue of label noise in the intrusion detection domain by presenting a framework to detect the samples with noisy labels. The decision tree classification algorithm and active learning are the main components of the proposed framework. The use of the framework is composed of two steps: making a decision tree robust against the label noise in a dataset and then using this robust model with the help of active learning with uncertainty sampling to detect noisy samples effectively. In this way, the inherent resiliency of the decision tree algorithm against label noise is utilized to tackle this issue in datasets. Based on the results of our experiments, the proposed framework can detect a considerable number of noisy samples in the training dataset, with up to 98% noise reduction.