Abstract—The present paper looks at the security problems caused by the fast growth of the Internet of Things (IoT) in areas like industry, healthcare, and agriculture. As IoT systems become more common, they face more threats from cyberattacks like Brute Force, Denial of Service (DoS), Botnets, and so ones. To deal with these security issues, we studied recent papers to review different intrusion detection systems made for IoT. The goal was to see how well they work and find ways to make them better. Hence, we have selected 63 relevant papers among 1200 find papers. These selected papers were published between 2020 and 2024. Our study shows that deep learning-based intrusion detection systems can improve the manner how online threats are detect. These systems, especially when they use neural networks, are better at spotting and reacting to harmful activities. Combining machine learning with Intrusion Detection Systems (IDS) seems to help boost the security of internet of things networks, offering stronger protection against cyber-attacks. One of the best algorithms we found was the combination of a Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM) network. This deep learning model showed very high accuracy in protecting IoT networks, especially when tested with different datasets. This proves that using advanced algorithms is important to keep up with the growing challenges of cyber-threats targeting IoT systems.
 
Keywords—Internet of Things (IoT), security, intrusion detection, Intrusion Detection Systems (IDS), deep learning, neural networks, Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM)


Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).