Sunoh Choi

Prof. Dr. Sunoh Choi


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 November 2024 in Electronics
Verified
Journal Article
Open access
PDF file
ACAbhishek Chaudhary
Abhishek Chaudhary
JHJunseo Han
Junseo Han
SKSeongah Kim
Seongah Kim
AKAram Kim
Aram Kim
SCSunoh Choi
Sunoh Choi
Industries are increasingly adopting digital systems to improve control and accessibility by providing real-time monitoring and early alerts for potential issues. While digital transformation fuels exponential growth, it exposes these industries to cyberattacks. For critical sectors such as nuclear power plants, a cyberattack not only risks damaging the facility but also endangers human lives. In today’s digital world, enormous amounts of data are generated, and the analysis of these data can help ensure effectiveness, including security. In this study, we analyzed the data using a deep learning model for early detection of abnormal behavior. We first examined the Asherah Nuclear Power Plant simulator by initiating three different cyberattacks, each targeting a different system, thereby collecting and analyzing data from the simulator. Second, a Bi-LSTM model was used to detect anomalies in the simulator, which detected it before the plant’s protection system was activated in response to a threat. Finally, we applied explainable AI (XAI) to acquire insight into how distinctive features contribute to the detection of anomalies. XAI provides valuable explanations of model behavior by revealing how specific features influence anomaly detection during attacks. This research proposes an effective anomaly detection technique and interpretability to better understand counter-cyber threats in critical industries, such as nuclear plants.

12 July 2021 in Applied Sciences
Verified
Journal Article
Open access
PDF file
SCSunoh Choi
Sunoh Choi
The internet’s rapid growth has resulted in an increase in the number of malicious files. Recently, powershell scripts and Windows portable executable (PE) files have been used in malicious behaviors. To solve these problems, artificial intelligence (AI) based malware detection methods have been widely studied. Among AI techniques, the graph convolution network (GCN) was recently introduced. Here, we propose a malicious powershell detection method using a GCN. To use the GCN, we needed an adjacency matrix. Therefore, we proposed an adjacency matrix generation method using the Jaccard similarity. In addition, we show that the malicious powershell detection rate is increased by approximately 8.2% using GCN.

1 December 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
SCSunoh Choi
Sunoh Choi
JCJaehyuk Cho
Jaehyuk Cho
Owing to their wide application, Internet of Things systems have been the target of malicious attacks. These attacks included DoS, flood, SlowITe, malformed, and brute-force attacks. A dataset that includes these attacks was recently released. However, the attack detection accuracy reported in previous studies has not been satisfactory because the studies used too many features that are not important in detecting malicious message queue telemetry transport (MQTT) traffic. Therefore, this study aims to analyze these attacks. Herein, a novel feature extraction method is proposed that includes the source port index, TCP length, MQTT message type, keep alive, and connection acknowledgment. The attacks were classified using the Seq2Seq model. During the experiment, the accuracy of the proposed method was 99.97%, which is 7.33% higher than that of previously reported methods.

14 February 2022 in Electronics
Verified
Journal Article
Open access
PDF file
SCSunoh Choi
Sunoh Choi
Nowadays, many Korean users read news from portal sites like Naver and Daum. Users can comment on news articles on such sites, and some try to influence public opinion through their comments. Therefore, news users need to be analyzed. This study proposes a deep learning method to classify each user’s political stance. Further, a method is developed to evaluate how many similar comments each user writes, and another method is developed to evaluate the similarity of a user’s comments with other users’ comments. We collect approximately 2.68 million comments from hundreds of thousands of political news articles in April 2017. First, for the top 100 news users, we classify each user’s political stance with 92.3% accuracy by using only 20% of data for deep learning training. Second, an evaluation of how many similar comments each user writes reveals that six users score more than 80 points. Third, an evaluation of the similarity of each user’s comments to other users’ comments reveals that 10 users score more than 80 points. Thus, based on this study, it is possible to detect malicious commenters, thereby enhancing comment systems used in news portal websites.

8 June 2024 in Electronics
Verified
Journal Article
Open access
PDF file
YNYounSu Nam
YounSu Nam
SCSunoh Choi
Sunoh Choi
Web-based systems are used extensively in Korea because web standards have been adapted by the law (e.g., Electronic Government Act). Users can easily access web-based systems if they are connected to the Internet. However, distinguishing between malicious and benign access is very difficult and many potential vulnerabilities exist. In this study, we attempt to leak the information of other users without permission using a non-encrypted API and web source code analysis in a college web-based system. An experiment demonstrates that the information (e.g., other students’ course grades) can be leaked and abnormal data can be embedded in the request. In addition, we discuss methods for preventing such vulnerability attacks.

5 July 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
DLDeun Lee
Deun Lee
SCSunoh Choi
Sunoh Choi
In Korea, it is common to read and comment on news stories on portal sites. To influence public opinion, some people write comments repeatedly, some of which are similar to those posted by others. This has become a serious social issue. In our previous research, we collected approximately 2.68 million news comments posted in April 2017. We classified the political stance of each author using a deep learning model (seq2seq), and evaluated how many similar comments each user wrote, as well as how similar each comment was to those posted by other people, using the Jaccard similarity coefficient. However, as our previous model used Jaccard’s similarity only, the meaning of the comments was not considered. To solve this problem, we propose similar word replacement (SWR) using word2vec and a method to analyze the similarity between user comments and classify the political stance of each user. In this study, we showed that when our model used SWR rather than Jaccard’s similarity, its ability to detect similarity between comments increased 3.2 times, and the accuracy of political stance classification improved by 6%.