Deep learning for cyber threat detection in IoT networks: A review

Abstract

The Internet of Things (IoT) has revolutionized modern tech with interconnected smart devices. While these innovations offer unprecedented opportunities, they also introduce complex security challenges. Cybersecurity is a pivotal concern for intrusion detection systems (IDS). Deep Learning has shown promise in effectively detecting and preventing cyberattacks on IoT devices. Although IDS is vital for safeguarding sensitive information by identifying and mitigating suspicious activities, conventional IDS solutions grapple with challenges in the IoT context. This paper delves into the cutting-edge intrusion detection methods for IoT security, anchored in Deep Learning. We review recent advancements in IDS for IoT, highlighting the underlying deep learning algorithms, associated datasets, types of attacks, and evaluation metrics. Further, we discuss the challenges faced in deploying Deep Learning for IoT security and suggest potential areas for future research. This survey will guide researchers and industry experts in adopting Deep Learning techniques in IoT security and intrusion detection.