The research team of Professor Jae-Hyuk Cho from the Department of Software Engineering, Jeonbuk National University (JBNU), received the ICT Express Best Paper Award for a paper published in the international journal ICT Express. The award ceremony was held at the 17th International Conference on Ubiquitous and Future Networks (ICUFN 2026), held in Milan, Italy, from the 7th to the 10th.

The awarded paper, 'Deep learning-driven methods for network-based intrusion detection systems: A systematic review', was published in ICT Express, Volume 11, Issue 1 (pp. 181–215, 2025).

This award is the most prestigious honor presented to the most outstanding research or review paper published in the SCIE-indexed international journal ICT Express, published by Elsevier. The selection committee determines the winner by comprehensively evaluating the paper's completeness, originality, academic contribution, and citation record.

The paper is a systematic literature review on network-based intrusion detection systems (NIDS) using deep learning. Following the PRISMA 2020 guidelines, the international standard for systematic reviews, the research team selected and analyzed relevant studies published between 2018 and 2024.

The paper compares and summarizes the characteristics and performance of major deep learning architectures used for intrusion detection, including convolutional neural networks (CNN), long short-term memory (LSTM), gated recurrent units (GRU), bidirectional LSTM (BiLSTM), and hybrid models. It also reviewed representative datasets, data preprocessing techniques, and performance evaluation metrics, and identified the limitation that traditional datasets such as NSL-KDD and KDD-CUP99 do not sufficiently reflect recent attack types.

It also analyzed key application domains for intrusion detection technologies—such as the Internet of Things (IoT), healthcare, and smart cities—and presented tools and platforms that can be used to implement deep learning-based intrusion detection systems, along with future research directions. The work is significant in that it provides structured reference points useful to both researchers and practitioners.

Professor Jae-Hyuk Cho said, "Although research on deep learning-based intrusion detection is rapidly increasing, methodologies and datasets are scattered, making it difficult to grasp the overall trend. I hope this paper serves as a systematic starting point for related researchers and practitioners, and we will continue research that can be applied to real security environments."