Ah Reum Kang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Ah Reum Kang has a total of 72 co-authors. Here are the top co-authors by number of shared publications:
- Huy Kang Kim
School of Cybersecurity, Korea University, Seoul, Republic of Korea
14 shared publications - Young-Seob Jeong
Chungbuk National University
11 shared publications - Jiyoung Woo
Department of Future Convergence Technology, Soonchunhyang University, Asan 31538, Republic of Korea
10 shared publications Aziz Mohaisen
SUNY Buffalo, USA
8 shared publicationsJiyoung Woo
SCH Media Labs, Soonchunhyang University, Asan, Chungnam, South Korea
5 shared publicationsJuyong Park
Korea Advanced Institute of Science & Technology, Daejeon, South Korea
5 shared publications
Latest Publications
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 154150-154167
A Feasibility Study of Treatment-Anchored Silver Labeling for Phenotyping Using VitalDB and Interpretable Machine Learning
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 154150-154167
Open AccessA Feasibility Study of Treatment-Anchored Silver Labeling for Phenotyping Using VitalDB and Interpretable Machine Learning
- Open Access
- 13 October 2025
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 20 (10) , e0332307
Malware detection using pre-trained transformer encoder with byte sequences
Ordinary users encounter various documents on the network every day, such as news articles, emails, and messages, and most are vulnerable to malicious attacks. Malicious attack methods continue to evolve, making neural network-based malware detection increasingly appealing to both academia and industry. Recent studies have leveraged byte sequences within files to detect malicious activities, primarily using convolutional neural networks to capture local patterns in the byte sequences. Meanwhile, in natural language processing, Transformer-based language models have demonstrated superior performance across various tasks and have been applied to other domains, such as image analysis and speech recognition. In this paper, we introduce a novel Transformer-based language model for malware detection that processes byte sequences as input. We propose two new pre-training strategies: real-or-fake prediction and same-sequence prediction. Including conventional pre-training strategies such as masked language modeling and next-sentence prediction, we explore all possible combinations of these approaches. By compiling existing byte sequences for malware detection, we construct a benchmark consisting of three file types (PDF, HWP, and MS Office) for pre-training and fine-tuning. Our empirical results demonstrate that our language model outperforms convolutional neural networks in the malware detection task, achieving a macro F1 score improvement of approximately 2.7%p∼11.1%p. We believe our language model will serve as a foundation model for malware detection services, and will extend our research to develop a more powerful encoder-based model that can process longer byte sequences.
- 13 October 2025
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 20 (10) , e0332307
Open AccessMalware detection using pre-trained transformer encoder with byte sequences
Ordinary users encounter various documents on the network every day, such as news articles, emails, and messages, and most are vulnerable to malicious attacks. Malicious attack methods continue to evolve, making neural network-based malware detection increasingly appealing to both academia and industry. Recent studies have leveraged byte sequences within files to detect malicious activities, primarily using convolutional neural networks to capture local patterns in the byte sequences. Meanwhile, in natural language processing, Transformer-based language models have demonstrated superior performance across various tasks and have been applied to other domains, such as image analysis and speech recognition. In this paper, we introduce a novel Transformer-based language model for malware detection that processes byte sequences as input. We propose two new pre-training strategies: real-or-fake prediction and same-sequence prediction. Including conventional pre-training strategies such as masked language modeling and next-sentence prediction, we explore all possible combinations of these approaches. By compiling existing byte sequences for malware detection, we construct a benchmark consisting of three file types (PDF, HWP, and MS Office) for pre-training and fine-tuning. Our empirical results demonstrate that our language model outperforms convolutional neural networks in the malware detection task, achieving a macro F1 score improvement of approximately 2.7%p∼11.1%p. We believe our language model will serve as a foundation model for malware detection services, and will extend our research to develop a more powerful encoder-based model that can process longer byte sequences.
- Open Access
- 10 March 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (6) , 2978
Deep Defense Against Mal-Doc: Utilizing Transformer and SeqGAN for Detecting and Classifying Document Type Malware
The prevalence of non-executable malware is on the rise, presenting a major threat to users, including major public institutions and corporations. While extensive research has been conducted on detecting malware threats, there is a noticeable gap in studying document-type malware compared with executable files. The proposed model will solve this gap by detecting and classifying document-type malware families using script codes, including tags, to write documents and script languages to execute malicious functions. These script codes offer insights into how the malware was constructed and operates on the victim’s system. Additionally, we leverage language models in our approach. Initially, we develop MalCode2Vec to learn associations between source codes and represent them as numeric vectors. Subsequently, we design a Transformer-based model for document malware detection and family classification. Detection is conducted at both the stream and file levels. To solve the class imbalance issue in the malware family, we utilize a generative adversarial network to generate malware samples. Our experimental domain focuses on the Hangul (Korean) word processor, a tool notably used by North Korea in targeting the South Korean government.
- 10 March 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (6) , 2978
Open AccessDeep Defense Against Mal-Doc: Utilizing Transformer and SeqGAN for Detecting and Classifying Document Type Malware
The prevalence of non-executable malware is on the rise, presenting a major threat to users, including major public institutions and corporations. While extensive research has been conducted on detecting malware threats, there is a noticeable gap in studying document-type malware compared with executable files. The proposed model will solve this gap by detecting and classifying document-type malware families using script codes, including tags, to write documents and script languages to execute malicious functions. These script codes offer insights into how the malware was constructed and operates on the victim’s system. Additionally, we leverage language models in our approach. Initially, we develop MalCode2Vec to learn associations between source codes and represent them as numeric vectors. Subsequently, we design a Transformer-based model for document malware detection and family classification. Detection is conducted at both the stream and file levels. To solve the class imbalance issue in the malware family, we utilize a generative adversarial network to generate malware samples. Our experimental domain focuses on the Hangul (Korean) word processor, a tool notably used by North Korea in targeting the South Korean government.
- Open Access
- 11 September 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (18) , 10196
Intelligent Anomaly Detection System through Malware Image Augmentation in IIoT Environment Based on Digital Twin
Due to the recent rapid development of the ICT (Information and Communications Technology) field, the industrial sector is also experiencing rapid informatization. As a result, malware targeting information leakage and financial gain are increasingly found within IIoT (the Industrial Internet of Things). Moreover, the number of malware variants is rapidly increasing. Therefore, there is a pressing need for a safe and preemptive malware detection method capable of responding to these rapid changes. The existing malware detection method relies on specific byte sequence inclusion in a binary file. However, this method faces challenges in impacting the system or detecting variant malware. In this paper, we propose a data augmentation method based on an adversarial generative neural network to maintain a secure system and acquire necessary learning data. Specifically, we introduce a digital twin environment to safeguard systems and data. The proposed system creates fixed-size images from malware binaries in the virtual environment of the digital twin. Additionally, it generates new malware through an adversarial generative neural network. The image information produced in this manner is then employed for malware detection through deep learning. As a result, the detection performance, in preparation for the emergence of new malware, demonstrated high accuracy, exceeding 97%.
- 11 September 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (18) , 10196
Open AccessIntelligent Anomaly Detection System through Malware Image Augmentation in IIoT Environment Based on Digital Twin
Due to the recent rapid development of the ICT (Information and Communications Technology) field, the industrial sector is also experiencing rapid informatization. As a result, malware targeting information leakage and financial gain are increasingly found within IIoT (the Industrial Internet of Things). Moreover, the number of malware variants is rapidly increasing. Therefore, there is a pressing need for a safe and preemptive malware detection method capable of responding to these rapid changes. The existing malware detection method relies on specific byte sequence inclusion in a binary file. However, this method faces challenges in impacting the system or detecting variant malware. In this paper, we propose a data augmentation method based on an adversarial generative neural network to maintain a secure system and acquire necessary learning data. Specifically, we introduce a digital twin environment to safeguard systems and data. The proposed system creates fixed-size images from malware binaries in the virtual environment of the digital twin. Additionally, it generates new malware through an adversarial generative neural network. The image information produced in this manner is then employed for malware detection through deep learning. As a result, the detection performance, in preparation for the emergence of new malware, demonstrated high accuracy, exceeding 97%.
- Open Access
- 1 June 2023
- Published by Springer Nature in Scientific Reports
- Vol. 13 (1) , 1-7
File-level malware detection using byte streams
As more documents appear on the Internet, it becomes important to detect malware within the documents. Malware of non-executables might be more dangerous because people usually open them without worrying about inherent danger. Recently, deep learning models are used to analyze byte streams of the non-executables for malware detection. Although they have shown successful results, they are commonly designed for stream-level detection, but not for file-level detection. In this paper, we propose a new method that aggregates the stream-level results to get file-level results for malware detection. We demonstrate its effectiveness by experimental results with our annotated dataset, and show that it gives performance gain of 3.37–5.89% of F1 scores.
- 1 June 2023
- Published by Springer Nature in Scientific Reports
- Vol. 13 (1) , 1-7
Open AccessFile-level malware detection using byte streams
As more documents appear on the Internet, it becomes important to detect malware within the documents. Malware of non-executables might be more dangerous because people usually open them without worrying about inherent danger. Recently, deep learning models are used to analyze byte streams of the non-executables for malware detection. Although they have shown successful results, they are commonly designed for stream-level detection, but not for file-level detection. In this paper, we propose a new method that aggregates the stream-level results to get file-level results for malware detection. We demonstrate its effectiveness by experimental results with our annotated dataset, and show that it gives performance gain of 3.37–5.89% of F1 scores.
- Open Access
- 10 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 51041-51047
Malware Detection Using Byte Streams of Different File Formats
Malware detection is becoming more important task as we face more data on the Internet. Web users are vulnerable to non-executable files such as Word files and Hangul Word Processor files because they usually open such files without paying attention. As new infected non-executables keep appearing, deep-learning models are drawing attention because they are known to be effective and have better generalization power. Especially, the deep-learning models have been used to learn arbitrary patterns from byte streams, and they exhibited successful performance on malware detection task. Although there have been malware detection studies using the deep-learning models, they commonly aimed at a single file format and did not take using different formats into consideration. In this paper, we assume that different file formats may contribute to each other, and deep-learning models will have a better chance to learn more promising patterns for better performance. We demonstrate that this assumption is possible by experimental results with our annotated datasets of two different file formats (e.g., Portable Document Format (PDF) and Hangul Word Processor (HWP)).
- 10 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 51041-51047
Open AccessMalware Detection Using Byte Streams of Different File Formats
Malware detection is becoming more important task as we face more data on the Internet. Web users are vulnerable to non-executable files such as Word files and Hangul Word Processor files because they usually open such files without paying attention. As new infected non-executables keep appearing, deep-learning models are drawing attention because they are known to be effective and have better generalization power. Especially, the deep-learning models have been used to learn arbitrary patterns from byte streams, and they exhibited successful performance on malware detection task. Although there have been malware detection studies using the deep-learning models, they commonly aimed at a single file format and did not take using different formats into consideration. In this paper, we assume that different file formats may contribute to each other, and deep-learning models will have a better chance to learn more promising patterns for better performance. We demonstrate that this assumption is possible by experimental results with our annotated datasets of two different file formats (e.g., Portable Document Format (PDF) and Hangul Word Processor (HWP)).
- Open Access
Prediction of Postoperative Complications for Patients of End Stage Renal Disease
End stage renal disease (ESRD) is the last stage of chronic kidney disease that requires dialysis or a kidney transplant to survive. Many studies reported a higher risk of mortality in ESRD patients compared with patients without ESRD. In this paper, we develop a model to predict postoperative complications, major cardiac event, for patients who underwent any type of surgery. We compare several widely-used machine learning models through experiments with our collected data yellow of size 3220, and achieved F1 score of 0.797 with the random forest model. Based on experimental results, we found that features related to operation (e.g., anesthesia time, operation time, crystal, and colloid) have the biggest impact on model performance, and also found the best combination of features. We believe that this study will allow physicians to provide more appropriate therapy to the ESRD patients by providing information on potential postoperative complications.
Open AccessPrediction of Postoperative Complications for Patients of End Stage Renal Disease
End stage renal disease (ESRD) is the last stage of chronic kidney disease that requires dialysis or a kidney transplant to survive. Many studies reported a higher risk of mortality in ESRD patients compared with patients without ESRD. In this paper, we develop a model to predict postoperative complications, major cardiac event, for patients who underwent any type of surgery. We compare several widely-used machine learning models through experiments with our collected data yellow of size 3220, and achieved F1 score of 0.797 with the random forest model. Based on experimental results, we found that features related to operation (e.g., anesthesia time, operation time, crystal, and colloid) have the biggest impact on model performance, and also found the best combination of features. We believe that this study will allow physicians to provide more appropriate therapy to the ESRD patients by providing information on potential postoperative complications.
- Open Access
Developing an Individual Glucose Prediction Model Using Recurrent Neural Network
In this study, we propose a personalized glucose prediction model using deep learning for hospitalized patients who experience Type-2 diabetes. We aim for our model to assist the medical personnel who check the blood glucose and control the amount of insulin doses. Herein, we employed a deep learning algorithm, especially a recurrent neural network (RNN), that consists of a sequence processing layer and a classification layer for the glucose prediction. We tested a simple RNN, gated recurrent unit (GRU), and long-short term memory (LSTM) and varied the architectures to determine the one with the best performance. For that, we collected data for a week using a continuous glucose monitoring device. Type-2 inpatients are usually experiencing bad health conditions and have a high variability of glucose level. However, there are few studies on the Type-2 glucose prediction model while many studies performed on Type-1 glucose prediction. This work has a contribution in that the proposed model exhibits a comparative performance to previous works on Type-1 patients. For 20 in-hospital patients, we achieved an average root mean squared error (RMSE) of 21.5 and an Mean absolute percentage error (MAPE) of 11.1%. The GRU with a single RNN layer and two dense layers was found to be sufficient to predict the glucose level. Moreover, to build a personalized model, at most, 50% of data are required for training.
Open AccessDeveloping an Individual Glucose Prediction Model Using Recurrent Neural Network
In this study, we propose a personalized glucose prediction model using deep learning for hospitalized patients who experience Type-2 diabetes. We aim for our model to assist the medical personnel who check the blood glucose and control the amount of insulin doses. Herein, we employed a deep learning algorithm, especially a recurrent neural network (RNN), that consists of a sequence processing layer and a classification layer for the glucose prediction. We tested a simple RNN, gated recurrent unit (GRU), and long-short term memory (LSTM) and varied the architectures to determine the one with the best performance. For that, we collected data for a week using a continuous glucose monitoring device. Type-2 inpatients are usually experiencing bad health conditions and have a high variability of glucose level. However, there are few studies on the Type-2 glucose prediction model while many studies performed on Type-1 glucose prediction. This work has a contribution in that the proposed model exhibits a comparative performance to previous works on Type-1 patients. For 20 in-hospital patients, we achieved an average root mean squared error (RMSE) of 21.5 and an Mean absolute percentage error (MAPE) of 11.1%. The GRU with a single RNN layer and two dense layers was found to be sufficient to predict the glucose level. Moreover, to build a personalized model, at most, 50% of data are required for training.
- Open Access
Malware Detection of Hangul Word Processor Files Using Spatial Pyramid Average Pooling
Malware detection of non-executables has recently been drawing much attention because ordinary users are vulnerable to such malware. Hangul Word Processor (HWP) is software for editing non-executable text files and is widely used in South Korea. New malware for HWP files continues to appear because of the circumstances between South Korea and North Korea. There have been various studies to solve this problem, but most of them are limited because they require a large amount of effort to define features based on expert knowledge. In this study, we designed a convolutional neural network to detect malware within HWP files. Our proposed model takes a raw byte stream as input and predicts whether it contains malicious actions or not. To incorporate highly variable lengths of HWP byte streams, we propose a new padding method and a spatial pyramid average pooling layer. We experimentally demonstrate that our model is not only effective, but also efficient.
Open AccessMalware Detection of Hangul Word Processor Files Using Spatial Pyramid Average Pooling
Malware detection of non-executables has recently been drawing much attention because ordinary users are vulnerable to such malware. Hangul Word Processor (HWP) is software for editing non-executable text files and is widely used in South Korea. New malware for HWP files continues to appear because of the circumstances between South Korea and North Korea. There have been various studies to solve this problem, but most of them are limited because they require a large amount of effort to define features based on expert knowledge. In this study, we designed a convolutional neural network to detect malware within HWP files. Our proposed model takes a raw byte stream as input and predicts whether it contains malicious actions or not. To incorporate highly variable lengths of HWP byte streams, we propose a new padding method and a spatial pyramid average pooling layer. We experimentally demonstrate that our model is not only effective, but also efficient.
- Open Access
Comparative Analysis on Machine Learning and Deep Learning to Predict Post-Induction Hypotension
Hypotensive events in the initial stage of anesthesia can cause serious complications in the patients after surgery, which could be fatal. In this study, we intended to predict hypotension after tracheal intubation using machine learning and deep learning techniques after intubation one minute in advance. Meta learning models, such as random forest, extreme gradient boosting (Xgboost), and deep learning models, especially the convolutional neural network (CNN) model and the deep neural network (DNN), were trained to predict hypotension occurring between tracheal intubation and incision, using data from four minutes to one minute before tracheal intubation. Vital records and electronic health records (EHR) for 282 of 319 patients who underwent laparoscopic cholecystectomy from October 2018 to July 2019 were collected. Among the 282 patients, 151 developed post-induction hypotension. Our experiments had two scenarios: using raw vital records and feature engineering on vital records. The experiments on raw data showed that CNN had the best accuracy of 72.63%, followed by random forest (70.32%) and Xgboost (64.6%). The experiments on feature engineering showed that random forest combined with feature selection had the best accuracy of 74.89%, while CNN had a lower accuracy of 68.95% than that of the experiment on raw data. Our study is an extension of previous studies to detect hypotension before intubation with a one-minute advance. To improve accuracy, we built a model using state-of-art algorithms. We found that CNN had a good performance, but that random forest had a better performance when combined with feature selection. In addition, we found that the examination period (data period) is also important.
Open AccessComparative Analysis on Machine Learning and Deep Learning to Predict Post-Induction Hypotension
Hypotensive events in the initial stage of anesthesia can cause serious complications in the patients after surgery, which could be fatal. In this study, we intended to predict hypotension after tracheal intubation using machine learning and deep learning techniques after intubation one minute in advance. Meta learning models, such as random forest, extreme gradient boosting (Xgboost), and deep learning models, especially the convolutional neural network (CNN) model and the deep neural network (DNN), were trained to predict hypotension occurring between tracheal intubation and incision, using data from four minutes to one minute before tracheal intubation. Vital records and electronic health records (EHR) for 282 of 319 patients who underwent laparoscopic cholecystectomy from October 2018 to July 2019 were collected. Among the 282 patients, 151 developed post-induction hypotension. Our experiments had two scenarios: using raw vital records and feature engineering on vital records. The experiments on raw data showed that CNN had the best accuracy of 72.63%, followed by random forest (70.32%) and Xgboost (64.6%). The experiments on feature engineering showed that random forest combined with feature selection had the best accuracy of 74.89%, while CNN had a lower accuracy of 68.95% than that of the experiment on raw data. Our study is an extension of previous studies to detect hypotension before intubation with a one-minute advance. To improve accuracy, we built a model using state-of-art algorithms. We found that CNN had a good performance, but that random forest had a better performance when combined with feature selection. In addition, we found that the examination period (data period) is also important.