Enhancing IoT cyber attacks intrusion detection through GAN-based data augmentation and hybrid deep learning models for MQTT network protocol cyber attacks

In the evolving digital landscape, interconnected IoT networks are expanding fast. However, essential security measures are often lacking, which makes it vulnerable to cyber threats. Intrusion Detection Systems (IDSs) are crucial in combating these threats, but IDSs in the IoT domain face significant challenges; one of them is the existence of imbalanced data, where attack activities are underrepresented compared to normal activities. This becomes a problem when handling Machine Learning (ML) tasks to improve the system’s intrusion detection ability. This paper presents a novel solution by leveraging Generative Adversarial Networks (GANs) to create balanced datasets. Unlike traditional methods, our approach generates high-quality synthetic samples that maintain the intricate characteristics of the data, making it possible to improve detection accuracy. Additionally, we introduce three specialized IDSs designed to detect attacks on the lightweight Message Queuing Telemetry Transport (MQTT) protocol, utilizing hybrid Deep Learning (DL) algorithms (CNN-RNN, CNN-LSTM, and CNN-GRU). Experimental results, using a combination of both the original MQTT dataset and a newly generated dataset through GANs, demonstrate the better performance of the generated datasets in multi-class classification. This performance highlights the effectiveness of our GAN-based approach in improving detection accuracy at the same time that it reduces false positives. The ultimate objective is to develop an autonomous system tailored to safeguard IoT environments, providing a robust and adaptable solution to emerging cyber threats.