Abstract:
The Industrial Internet of Things (IIoT) has become one of the most rapidly developing innovative technologies in recent years, with the potential to digitize and connect...Show MoreMetadata
Abstract:
The Industrial Internet of Things (IIoT) has become one of the most rapidly developing innovative technologies in recent years, with the potential to digitize and connect numerous industries for enormous commercial prospects and growth of the global GDP. Industry, logistics, shipping, petroleum and natural gas, mining and metals, power utilities, and aviation are just a few of the diverse industries that employ IIoT. Even while the IIoT offers exciting potential for the creation of many industrial applications, these applications must meet more stringent security standards and are vulnerable to cyberattacks. Since there are so many sensors There is a tone of data in the IIoT networkis produced, which has caught the attention of hackers all around the world. The intrusion detection system (IDS), which monitors network traffic and identifies network activity, is one of the main security solutions for defending IIoT applications from threats. Recent research has shown that deep learning and machine learning techniques can enhance intrusion detection effectiveness and lessen a range of security risks. In this work, we provide an overview of IIoT-focused IDS techniques based on deep learning. Providing a range of deep learning-based IDS detection techniques, datasets, and comparative studies is the major goal of this effort. Ultimately, the goal of the study is to highlight the shortcomings and difficulties of past investigations.as well as possible alternatives and potential trends.
Date of Conference: 14-16 December 2022
Date Added to IEEE Xplore: 22 March 2023
ISBN Information: