AUTOENCODER-BASED MODEL FOR DETECTING IOT NETWORK TRAFFIC ANOMALIES

Abstract

Cyberattacks on computer networks are becoming increasingly sophisticated, particularly in Internet of Things (IoT) environments, where devices continuously generate large and complex amounts of data. Traditional security systems that rely on predefined rules or signatures often fail to detect new or evolving threats. Even deep learning methods, such as RNNs and CNNs, face challenges in handling dynamic traffic efficiently. To address these issues, this study introduces an autoencoder-based anomaly detection model that learns to identify abnormal network activities. The model was trained using Kaggle datasets containing both normal IoT traffic and malicious traffic from well-known botnets like Mirai and BASHLITE. By compressing network data into a latent space and reconstructing it, the model uses reconstruction error to detect unusual patterns that indicate anomalies. The experimental results were highly promising, achieving 99% accuracy, precision, recall, and F1-scores above 99%. Unlike previous studies that depend on simulated or cloud-based data, this research highlights the power of autoencoders for real-world IoT anomaly detection and lays a strong foundation for developing real-time intrusion detection systems.