Thi-Thu-Huong Le

Dr. Thi-Thu-Huong Le

Pusan National University, Busan, Republic of Korea
orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
1 February 2016
Verified
Conference Paper
Closed access
JKJihyun Kim
Jihyun Kim
JKJaehyun Kim
Jaehyun Kim
Thi-Thu-Huong LeThi-Thu-Huong Le
Thi-Thu-Huong Le
HKHowon Kim
Howon Kim
Due to the advance of information and communication techniques, sharing information through online has been increased. And this leads to creating the new added value. As a result, various online services were created. However, as increasing connection points to the internet, the threats of cyber security have also been increasing. Intrusion detection system(IDS) is one of the important security issues today. In this paper, we construct an IDS model with deep learning approach. We apply Long Short Term Memory(LSTM) architecture to a Recurrent Neural Network(RNN) and train the IDS model using KDD Cup 1999 dataset. Through the performance test, we confirm that the deep learning approach is effective for IDS.

3 February 2022 in Sensors
Verified
Journal Article
Open access
PDF file
Thi-Thu-Huong LeThi-Thu-Huong Le
Thi-Thu-Huong Le
HKHaeyoung Kim
Haeyoung Kim
HKHyoeun Kang
Hyoeun Kang
Howon KimHowon Kim
Howon Kim
In recent years, many methods for intrusion detection systems (IDS) have been designed and developed in the research community, which have achieved a perfect detection rate using IDS datasets. Deep neural networks (DNNs) are representative examples applied widely in IDS. However, DNN models are becoming increasingly complex in model architectures with high resource computing in hardware requirements. In addition, it is difficult for humans to obtain explanations behind the decisions made by these DNN models using large IoT-based IDS datasets. Many proposed IDS methods have not been applied in practical deployments, because of the lack of explanation given to cybersecurity experts, to support them in terms of optimizing their decisions according to the judgments of the IDS models. This paper aims to enhance the attack detection performance of IDS with big IoT-based IDS datasets as well as provide explanations of machine learning (ML) model predictions. The proposed ML-based IDS method is based on the ensemble trees approach, including decision tree (DT) and random forest (RF) classifiers which do not require high computing resources for training models. In addition, two big datasets are used for the experimental evaluation of the proposed method, NF-BoT-IoT-v2, and NF-ToN-IoT-v2 (new versions of the original BoT-IoT and ToN-IoT datasets), through the feature set of the net flow meter. In addition, the IoTDS20 dataset is used for experiments. Furthermore, the SHapley additive exPlanations (SHAP) is applied to the eXplainable AI (XAI) methodology to explain and interpret the classification decisions of DT and RF models; this is not only effective in interpreting the final decision of the ensemble tree approach but also supports cybersecurity experts in quickly optimizing and evaluating the correctness of their judgments based on the explanations of the results.

16 July 2022 in Sustainability
Verified
Journal Article
Open access
PDF file
Thi-Thu-Huong LeThi-Thu-Huong Le
Thi-Thu-Huong Le
YOYustus Oktian
Yustus Oktian
Howon KimHowon Kim
Howon Kim
The Industrial Internet of Things (IIoT) has advanced digital technology and the fastest interconnection, which creates opportunities to substantially grow industrial businesses today. Although IIoT provides promising opportunities for growth, the massive sensor IoT data collected are easily attacked by cyber criminals. Hence, IIoT requires different high security levels to protect the network. An Intrusion Detection System (IDS) is one of the crucial security solutions, which aims to detect the network’s abnormal behavior and monitor safe network traffic to avoid attacks. In particular, the effectiveness of the Machine Learning (ML)-based IDS approach to building a secure IDS application is attracting the security research community in both the general cyber network and the specific IIoT network. However, most available IIoT datasets contain multiclass output data with imbalanced distributions. This is the main reason for the reduction in the detection accuracy of attacks of the ML-based IDS model. This research proposes an IDS for IIoT imbalanced datasets by applying the eXtremely Gradient Boosting (XGBoost) model to overcome this issue. Two modern IIoT imbalanced datasets were used to assess our proposed method’s effectiveness and robustness, X-IIoTDS and TON_IoT. The XGBoost model achieved excellent attack detection with F1 scores of 99.9% and 99.87% on the two datasets. This result demonstrated that the proposed approach improved the detection attack performance in imbalanced multiclass IIoT datasets and was superior to existing IDS frameworks.

2 October 2017 in Computational Intelligence and Neuroscience
Verified
Journal Article
Open access
PDF file
JKJihyun Kim
Jihyun Kim
Thi-Thu-Huong LeThi-Thu-Huong Le
Thi-Thu-Huong Le
HKHowon Kim
Howon Kim
Monitoring electricity consumption in the home is an important way to help reduce energy usage. Nonintrusive Load Monitoring (NILM) is existing technique which helps us monitor electricity consumption effectively and costly. NILM is a promising approach to obtain estimates of the electrical power consumption of individual appliances from aggregate measurements of voltage and/or current in the distribution system. Among the previous studies, Hidden Markov Model (HMM) based models have been studied very much. However, increasing appliances, multistate of appliances, and similar power consumption of appliances are three big issues in NILM recently. In this paper, we address these problems through providing our contributions as follows. First, we proposed state-of-the-art energy disaggregation based on Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) model and additional advanced deep learning. Second, we proposed a novel signature to improve classification performance of the proposed model in multistate appliance case. We applied the proposed model on two datasets such as UK-DALE and REDD. Via our experimental results, we have confirmed that our model outperforms the advanced model. Thus, we show that our combination between advanced deep learning and novel signature can be a robust solution to overcome NILM’s issues and improve the performance of load identification.

17 March 2021 in IEEE Transactions on Smart Grid
Verified
Journal Article
Closed access
Thi-Thu-Huong LeThi-Thu-Huong Le
Thi-Thu-Huong Le
SHShinwook Heo
Shinwook Heo
Howon KimHowon Kim
Howon Kim
Load identification is a core concept in non-intrusive load monitoring (NILM). Through NILM systems, users can check their home appliance usage habits and then adjust their behavior to save electricity. In this way, a NILM system offers an effective method to detect the event status of household appliances as well as individual loads' energy consumption. However, prior NILM methods have encountered a challenge in improving recognition accuracy for both linear load and non-linear load types. These methods used a representative feature, namely transient load signals. However, the transient signals on these loads differ in terms of transient time and transient shape, which is the main cause of reduced accuracy performance in load identification. To this end, this paper presents a novel method, HT-LSTM (Hilbert Transform Long Short-Term Memory), which enhances recognition of the various load types that contain the difference in the transient time and the transient shape of any load signal. The proposed method consists of two main parts: (i) generating a novel transient feature based on a Hilbert transform (HT), called APF (Amplitude-Phase-Frequency). APF features are sequential data, which is used for the classification model; and (ii) applying Sequence-to-Sequence Long Short-Term Memory (Seq2Seq LSTM) to identify appliances by using APF features as the input data. In this work, we evaluate the HT-LSTM method using two high-frequency public datasets, Building-Level fUlly-labeled dataset for Electricity Disaggregation (BLUED) and Plug Load Appliance Identification Dataset (PLAID). Also, we evaluate our method using a private dataset collected in the lab. Based on the experimental results obtained and comparison classification performance pointed, the proposed method outperforms previous methods of F-score measurement on both public datasets in load identification as well as the private dataset.

3 April 2019 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Thi-Thu-Huong LeThi-Thu-Huong Le
Thi-Thu-Huong Le
YKYongsu Kim
Yongsu Kim
Howon KimHowon Kim
Howon Kim
The recent increase in hacks and computer network attacks around the world has intensified the need to develop better intrusion detection and prevention systems. The intrusion detection system (IDS) plays a vital role in detecting anomalies and attacks on the network which have become larger and more pervasive in nature. However, most anomaly-based intrusion detection systems are plagued by high false positives. Furthermore, Remote-to-Local (R2L) and User-to-Root (U2R) are two kinds of attack which have low predicted accuracy scores in advance IDS methods. Therefore, this paper proposes a novel IDS framework to overcome these IDS problems. The proposed framework including three main parts. The first part is to build SFSDT model which is the feature selection model. SFSDT is to generate the best feature subset from the original feature set. This model is a hybrid Sequence Forward Selection (SFS) algorithm and Decision Tree (DT) model. The second part is to build various IDS models to train on the best-selected feature subset. The various Recurrent Neural Networks (RNN) are traditional RNN, Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU). Two IDS datasets are used for the learned models in experiments including NSL-KDD in 2010 and ISCX in 2012. The final part is to evaluate the proposed model by comparing the proposed models to other IDS models. The experimental results show the proposed models achieve significantly improved accuracy detection rate as well as attack types classification. Furthermore, this approach can reduce the computation time by memory profilers measurement.