An Anomaly Detection Model for IoT Networks based on Flow and Flag Features using a Feed-Forward Neural Network
Imtiaz Ullah, Qusay H. Mahmoud
Abstract
The security of IoT networks is becoming increasingly challenging, and anomaly detection for IoT network traffic is a critical technique for addressing this issue. However, extracting precise and effective network traffic features for anomaly detection is challenging. To address this issue, the current research analyzes various types of network flow features. In this paper, we present the design and development of an anomalous activity detection system for IoT networks based on flow and control flags features using a feed-forward neural network. The model has been evaluated using BoT-IoT, IoT network intrusion, MQTT-IoT-IDS2020, MQTTset, IoT-23, and IoT-DS2 datasets for binary and multiclass classification. Our proposed binary and multiclass classification model attained high accuracy, precision, recall, and F1 score compared to existing deep learning implementations.