Haemin Jung
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
Haemin Jung has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Wooju Kim
Affiliation Department of Industrial Engineering, Yonsei University, Seoul, Republic of Korea
4 shared publications - Kwangyon Lee
Soongsil Univ, Sch Elect Engn, Seoul 06978, South Korea
2 shared publications - Heesung Park
Department of Industrial Engineering, Yonsei University, Seodaemun-gu, Seoul 03722, Republic of Korea
1 shared publication - June Seok Hong
Department of Management Information Systems, Kyonggi University, Gyeonggi-do 16227, Korea
1 shared publication - Junghee Kim
Department of Industrial Engineering, Yonsei University, Seoul 03722, Korea
1 shared publication Sangho Son
Department of Industrial Engineering, Yonsei University, Seoul, 03722, Republic of Korea
1 shared publication
Latest Publications
- Open Access
- 1 January 2025
- Published by Tech Science Press in Computers, Materials & Continua
- Vol. 85 (2) , 2893-2912
Adapting Convolutional Autoencoder for DDoS Attack Detection via Joint Reconstruction Learning and Refined Anomaly Scoring
As cyber threats become increasingly sophisticated, Distributed Denial-of-Service (DDoS) attacks continue to pose a serious threat to network infrastructure, often disrupting critical services through overwhelming traffic. Although unsupervised anomaly detection using convolutional autoencoders (CAEs) has gained attention for its ability to model normal network behavior without requiring labeled data, conventional CAEs struggle to effectively distinguish between normal and attack traffic due to over-generalized reconstructions and naive anomaly scoring. To address these limitations, we propose CA-CAE, a novel anomaly detection framework designed to improve DDoS detection through asymmetric joint reconstruction learning and refined anomaly scoring. Our architecture connects two CAEs sequentially with asymmetric filter allocation, which amplifies reconstruction errors for anomalous data while preserving low errors for normal traffic. Additionally, we introduce a scoring mechanism that incorporates exponential decay weighting to emphasize recent anomalies and relative traffic volume adjustment to highlight high-risk instances, enabling more accurate and timely detection. We evaluate CA-CAE on a real-world network traffic dataset collected using Cisco NetFlow, containing over 190,000 normal instances and only 78 anomalous instances—an extremely imbalanced scenario (0.0004% anomalies). We validate the proposed framework through extensive experiments, including statistical tests and comparisons with baseline models. Despite this challenge, our method achieves significant improvement, increasing the F1-score from 0.515 obtained by the baseline CAE to 0.934, and outperforming other models. These results demonstrate the effectiveness, scalability, and practicality of CA-CAE for unsupervised DDoS detection in realistic network environments. By combining lightweight model architecture with a domain-aware scoring strategy, our framework provides a robust solution for early detection of DDoS attacks without relying on labeled attack data.
- 1 January 2025
- Published by Tech Science Press in Computers, Materials & Continua
- Vol. 85 (2) , 2893-2912
Open AccessAdapting Convolutional Autoencoder for DDoS Attack Detection via Joint Reconstruction Learning and Refined Anomaly Scoring
As cyber threats become increasingly sophisticated, Distributed Denial-of-Service (DDoS) attacks continue to pose a serious threat to network infrastructure, often disrupting critical services through overwhelming traffic. Although unsupervised anomaly detection using convolutional autoencoders (CAEs) has gained attention for its ability to model normal network behavior without requiring labeled data, conventional CAEs struggle to effectively distinguish between normal and attack traffic due to over-generalized reconstructions and naive anomaly scoring. To address these limitations, we propose CA-CAE, a novel anomaly detection framework designed to improve DDoS detection through asymmetric joint reconstruction learning and refined anomaly scoring. Our architecture connects two CAEs sequentially with asymmetric filter allocation, which amplifies reconstruction errors for anomalous data while preserving low errors for normal traffic. Additionally, we introduce a scoring mechanism that incorporates exponential decay weighting to emphasize recent anomalies and relative traffic volume adjustment to highlight high-risk instances, enabling more accurate and timely detection. We evaluate CA-CAE on a real-world network traffic dataset collected using Cisco NetFlow, containing over 190,000 normal instances and only 78 anomalous instances—an extremely imbalanced scenario (0.0004% anomalies). We validate the proposed framework through extensive experiments, including statistical tests and comparisons with baseline models. Despite this challenge, our method achieves significant improvement, increasing the F1-score from 0.515 obtained by the baseline CAE to 0.934, and outperforming other models. These results demonstrate the effectiveness, scalability, and practicality of CA-CAE for unsupervised DDoS detection in realistic network environments. By combining lightweight model architecture with a domain-aware scoring strategy, our framework provides a robust solution for early detection of DDoS attacks without relying on labeled attack data.
- Open Access
- 31 December 2024
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 19 (12) , e0316454
NATE: Non-pArameTric approach for Explainable credit scoring on imbalanced class
Credit scoring models play a crucial role for financial institutions in evaluating borrower risk and sustaining profitability. Logistic regression is widely used in credit scoring due to its robustness, interpretability, and computational efficiency; however, its predictive power decreases when applied to complex or non-linear datasets, resulting in reduced accuracy. In contrast, tree-based machine learning models often provide enhanced predictive performance but struggle with interpretability. Furthermore, imbalanced class distributions, which are prevalent in credit scoring, can adversely impact model accuracy and robustness, as the majority class tends to dominate. Despite these challenges, research that comprehensively addresses both the predictive performance and explainability aspects within the credit scoring domain remains limited. This paper introduces the Non-pArameTric oversampling approach for Explainable credit scoring (NATE), a framework designed to address these challenges by combining oversampling techniques with tree-based classifiers to enhance model performance and interpretability. NATE incorporates class balancing methods to mitigate the impact of imbalanced data distributions and integrates interpretability features to elucidate the model’s decision-making process. Experimental results show that NATE substantially outperforms traditional logistic regression in credit risk classification, with improvements of 19.33% in AUC, 71.56% in MCC, and 85.33% in F1 Score. Oversampling approaches, particularly when used with gradient boosting, demonstrated superior effectiveness compared to undersampling, achieving optimal metrics of AUC: 0.9649, MCC: 0.8104, and F1 Score: 0.9072. Moreover, NATE enhances interpretability by providing detailed insights into feature contributions, aiding in understanding individual predictions. These findings highlight NATE’s capability in managing class imbalance, improving predictive performance, and enhancing model interpretability, demonstrating its potential as a reliable and transparent tool for credit scoring applications.
- 31 December 2024
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 19 (12) , e0316454
Open AccessNATE: Non-pArameTric approach for Explainable credit scoring on imbalanced class
Credit scoring models play a crucial role for financial institutions in evaluating borrower risk and sustaining profitability. Logistic regression is widely used in credit scoring due to its robustness, interpretability, and computational efficiency; however, its predictive power decreases when applied to complex or non-linear datasets, resulting in reduced accuracy. In contrast, tree-based machine learning models often provide enhanced predictive performance but struggle with interpretability. Furthermore, imbalanced class distributions, which are prevalent in credit scoring, can adversely impact model accuracy and robustness, as the majority class tends to dominate. Despite these challenges, research that comprehensively addresses both the predictive performance and explainability aspects within the credit scoring domain remains limited. This paper introduces the Non-pArameTric oversampling approach for Explainable credit scoring (NATE), a framework designed to address these challenges by combining oversampling techniques with tree-based classifiers to enhance model performance and interpretability. NATE incorporates class balancing methods to mitigate the impact of imbalanced data distributions and integrates interpretability features to elucidate the model’s decision-making process. Experimental results show that NATE substantially outperforms traditional logistic regression in credit risk classification, with improvements of 19.33% in AUC, 71.56% in MCC, and 85.33% in F1 Score. Oversampling approaches, particularly when used with gradient boosting, demonstrated superior effectiveness compared to undersampling, achieving optimal metrics of AUC: 0.9649, MCC: 0.8104, and F1 Score: 0.9072. Moreover, NATE enhances interpretability by providing detailed insights into feature contributions, aiding in understanding individual predictions. These findings highlight NATE’s capability in managing class imbalance, improving predictive performance, and enhancing model interpretability, demonstrating its potential as a reliable and transparent tool for credit scoring applications.
- Open Access
- 27 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 7273-7283
Knowledge Graph as Pre-Training Corpus for Structural Reasoning via Multi-Hop Linearization
Large language models have demonstrated exceptional performance across various natural language processing tasks. However, their reliance on unstructured text corpora for pre-training limits their effectiveness in tasks requiring structured reasoning such as multi-hop question-answering. Knowledge Graphs provide a rich, structured source of relational data, offering an opportunity to enhance the reasoning capabilities of Large language models. In this paper, we propose a novel framework, Knowledge Graph as Pre-training Corpus (KGPC), which transforms knowledge graphs into text using a multi-hop linearization process. Unlike existing approaches that linearize singular triples, our method captures the interconnected nature of knowledge graphs by linking multiple triples across multiple hops, preserving their relational structure during the pre-training phase. This structured knowledge injection improves language models’ abilities to perform complex reasoning tasks.We evaluate our approach on multi-hop reasoning benchmarks, demonstrating significant performance gains over existing models, particularly in question-answering tasks. Our results highlight the potential of multi-hop linearization in enhancing the structural reasoning capacity of language models, reducing error propagation, and improving the integration of structured knowledge into language models.
- 27 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 7273-7283
Open AccessKnowledge Graph as Pre-Training Corpus for Structural Reasoning via Multi-Hop Linearization
Large language models have demonstrated exceptional performance across various natural language processing tasks. However, their reliance on unstructured text corpora for pre-training limits their effectiveness in tasks requiring structured reasoning such as multi-hop question-answering. Knowledge Graphs provide a rich, structured source of relational data, offering an opportunity to enhance the reasoning capabilities of Large language models. In this paper, we propose a novel framework, Knowledge Graph as Pre-training Corpus (KGPC), which transforms knowledge graphs into text using a multi-hop linearization process. Unlike existing approaches that linearize singular triples, our method captures the interconnected nature of knowledge graphs by linking multiple triples across multiple hops, preserving their relational structure during the pre-training phase. This structured knowledge injection improves language models’ abilities to perform complex reasoning tasks.We evaluate our approach on multi-hop reasoning benchmarks, demonstrating significant performance gains over existing models, particularly in question-answering tasks. Our results highlight the potential of multi-hop linearization in enhancing the structural reasoning capacity of language models, reducing error propagation, and improving the integration of structured knowledge into language models.
- Open Access
- 6 September 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (18) , 10041
Enhancing Recommender Systems with Semantic User Profiling through Frequent Subgraph Mining on Knowledge Graphs
Recommender systems play a crucial role in personalizing online user experiences by creating user profiles based on user–item interactions and preferences. Knowledge graphs (KGs) are intricate data structures that encapsulate semantic information, expressing users and items in a meaningful way. Although recent deep learning-based recommendation algorithms that embed KGs have demonstrated impressive performance, the richness of semantics and explainability embedded in the KGs are often lost due to the opaque nature of vector representations in deep neural networks. To address this issue, we propose a novel user profiling method for recommender systems that can encapsulate user preferences while preserving the original semantics of the KGs, using frequent subgraph mining. Our approach involves creating user profile vectors from a set of frequent subgraphs that contain information about user preferences and the strength of those preferences, measured by frequency. Subsequently, we trained a deep neural network model to learn the relationship between users and items, thereby facilitating effective recommendations using the neural network’s approximation ability. We evaluated our user profiling methodology on movie data and found that it demonstrated competitive performance, indicating that our approach can accurately represent user preferences while maintaining the semantics of the KGs. This work, therefore, presents a significant step towards creating more transparent and effective recommender systems that can be beneficial for a wide range of applications and readers interested in this field.
- 6 September 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (18) , 10041
Open AccessEnhancing Recommender Systems with Semantic User Profiling through Frequent Subgraph Mining on Knowledge Graphs
Recommender systems play a crucial role in personalizing online user experiences by creating user profiles based on user–item interactions and preferences. Knowledge graphs (KGs) are intricate data structures that encapsulate semantic information, expressing users and items in a meaningful way. Although recent deep learning-based recommendation algorithms that embed KGs have demonstrated impressive performance, the richness of semantics and explainability embedded in the KGs are often lost due to the opaque nature of vector representations in deep neural networks. To address this issue, we propose a novel user profiling method for recommender systems that can encapsulate user preferences while preserving the original semantics of the KGs, using frequent subgraph mining. Our approach involves creating user profile vectors from a set of frequent subgraphs that contain information about user preferences and the strength of those preferences, measured by frequency. Subsequently, we trained a deep neural network model to learn the relationship between users and items, thereby facilitating effective recommendations using the neural network’s approximation ability. We evaluated our user profiling methodology on movie data and found that it demonstrated competitive performance, indicating that our approach can accurately represent user preferences while maintaining the semantics of the KGs. This work, therefore, presents a significant step towards creating more transparent and effective recommender systems that can be beneficial for a wide range of applications and readers interested in this field.
- Open Access
- 8 August 2022
- Published by MDPI AG in Sustainability
- Vol. 14 (15) , 9791
Sequential Pattern Mining Approach for Personalized Fraudulent Transaction Detection in Online Banking
Financial institutions face challenges of fraud due to an increased number of online transactions and sophisticated fraud techniques. Although fraud detection systems have been implemented to detect fraudulent transactions in online banking, many systems just use conventional rule-based approaches. Rule-based detection systems have a difficulty in updating and managing their rules and conditions manually. Additionally, generated from the few fraud cases, the rules are general rather than specific to each user. In this paper, we propose a personalized alarm model to detect frauds in online banking transactions using sequence pattern mining on each user’s normal transaction log. We assumed that a personalized fraud detection model is more effective in responding to the rapid increase in online banking users and diversified fraud patterns. Moreover, we focused on the fact that fraudulent transactions are very different from each user’s usual transactions. Our proposed model divides each user’s log into transactions, extracts a set of sequence patterns, and uses it to determine whether a new incoming transaction is fraudulent. The incoming transaction is divided into multiple windows, and if the normal patterns are not found in the consecutive windows, an alarm is sounded. We applied the model to a real-world dataset and showed that our model outperforms the rule-based model and the Markov chain model. Although more experiments on additional datasets are needed, our personalized alarm model can be applied to real-world systems.
- 8 August 2022
- Published by MDPI AG in Sustainability
- Vol. 14 (15) , 9791
Open AccessSequential Pattern Mining Approach for Personalized Fraudulent Transaction Detection in Online Banking
Financial institutions face challenges of fraud due to an increased number of online transactions and sophisticated fraud techniques. Although fraud detection systems have been implemented to detect fraudulent transactions in online banking, many systems just use conventional rule-based approaches. Rule-based detection systems have a difficulty in updating and managing their rules and conditions manually. Additionally, generated from the few fraud cases, the rules are general rather than specific to each user. In this paper, we propose a personalized alarm model to detect frauds in online banking transactions using sequence pattern mining on each user’s normal transaction log. We assumed that a personalized fraud detection model is more effective in responding to the rapid increase in online banking users and diversified fraud patterns. Moreover, we focused on the fact that fraudulent transactions are very different from each user’s usual transactions. Our proposed model divides each user’s log into transactions, extracts a set of sequence patterns, and uses it to determine whether a new incoming transaction is fraudulent. The incoming transaction is divided into multiple windows, and if the normal patterns are not found in the consecutive windows, an alarm is sounded. We applied the model to a real-world dataset and showed that our model outperforms the rule-based model and the Markov chain model. Although more experiments on additional datasets are needed, our personalized alarm model can be applied to real-world systems.
- Open Access
- 20 January 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (3) , 932
Learning Knowledge Using Frequent Subgraph Mining from Ontology Graph Data
In many areas, vast amounts of information are rapidly accumulating in the form of ontology-based knowledge graphs, and the use of information in these forms of knowledge graphs is becoming increasingly important. This study proposes a novel method for efficiently learning frequent subgraphs (i.e., knowledge) from ontology-based graph data. An ontology-based large-scale graph is decomposed into small unit subgraphs, which are used as the unit to calculate the frequency of the subgraph. The frequent subgraphs are extracted through candidate generation and chunking processes. To verify the usefulness of the extracted frequent subgraphs, the methodology was applied to movie rating prediction. Using the frequent subgraphs as user profiles, the graph similarity between the rating graph and new item graph was calculated to predict the rating. The MovieLens dataset was used for the experiment, and a comparison showed that the proposed method outperformed other widely used recommendation methods. This study is meaningful in that it proposed an efficient method for extracting frequent subgraphs while maintaining semantic information and considering scalability in large-scale graphs. Furthermore, the proposed method can provide results that include semantic information to serve as a logical basis for rating prediction or recommendation, which existing methods are unable to provide.
- 20 January 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (3) , 932
Open AccessLearning Knowledge Using Frequent Subgraph Mining from Ontology Graph Data
In many areas, vast amounts of information are rapidly accumulating in the form of ontology-based knowledge graphs, and the use of information in these forms of knowledge graphs is becoming increasingly important. This study proposes a novel method for efficiently learning frequent subgraphs (i.e., knowledge) from ontology-based graph data. An ontology-based large-scale graph is decomposed into small unit subgraphs, which are used as the unit to calculate the frequency of the subgraph. The frequent subgraphs are extracted through candidate generation and chunking processes. To verify the usefulness of the extracted frequent subgraphs, the methodology was applied to movie rating prediction. Using the frequent subgraphs as user profiles, the graph similarity between the rating graph and new item graph was calculated to predict the rating. The MovieLens dataset was used for the experiment, and a comparison showed that the proposed method outperformed other widely used recommendation methods. This study is meaningful in that it proposed an efficient method for extracting frequent subgraphs while maintaining semantic information and considering scalability in large-scale graphs. Furthermore, the proposed method can provide results that include semantic information to serve as a logical basis for rating prediction or recommendation, which existing methods are unable to provide.
- 8 January 2020
- Published by Springer Nature in Journal of Intelligent Information Systems
- Vol. 55 (3) , 501-520
Automated conversion from natural language query to SPARQL query
- 8 January 2020
- Published by Springer Nature in Journal of Intelligent Information Systems
- Vol. 55 (3) , 501-520
Automated conversion from natural language query to SPARQL query