Kyungho Lee

Prof. Dr. Kyungho Lee

orcid

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

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

Representative Publications

View All Publications
25 September 2018 in Security and Communication Networks
Verified
Journal Article
Open access
PDF file
DCDahee Choi
Dahee Choi
Kyungho LeeKyungho Lee
Kyungho Lee
Financial fraud under IoT environment refers to the unauthorized use of mobile transaction using mobile platform through identity theft or credit card stealing to obtain money fraudulently. Financial fraud under IoT environment is the fast-growing issue through the emergence of smartphone and online transition services. In the real world, a highly accurate process of financial fraud detection under IoT environment is needed since financial fraud causes financial loss. Therefore, we have surveyed financial fraud methods using machine learning and deep learning methodology, mainly from 2016 to 2018, and proposed a process for accurate fraud detection based on the advantages and limitations of each research. Moreover, our approach proposed the overall process of detecting financial fraud based on machine learning and compared with artificial neural networks approach to detect fraud and process large amounts of financial data. To detect financial fraud and process large amounts of financial data, our proposed process includes feature selection, sampling, and applying supervised and unsupervised algorithms. The final model was validated by the actual financial transaction data occurring in Korea, 2015.

9 May 2019 in Sensors
Verified
Journal Article
Open access
PDF file
MPMookyu Park
Mookyu Park
HOHaengrok Oh
Haengrok Oh
Kyungho LeeKyungho Lee
Kyungho Lee
Internet-of-Things (IoT) is a technology that is extensively being used in various fields. Companies like Samsung, LG, and Apple are launching home appliances that use IoT as a part of their smart home business. Currently, Intelligent Things which combine artificial intelligence (AI) and IoT are being developed. Most of these devices are configured to collect and respond to human behavior (motion, voice, etc.) through built-in sensors. If IoT devices do not ensure high security, personal information could be leaked. This paper describes the IoT security threats that can cause information leakage from a hierarchical viewpoint of cyberspace. In addition, because these smart home-based IoT devices are closely related to human life, considering social damage is a problem. To overcome this, we propose a framework to measure the risk of IoT devices based on security scenarios that can occur in a smart home.

24 April 2020 in IEEE Access
Verified
Journal Article
Open access
AKAram Kim
Aram Kim
JOJunhyoung Oh
Junhyoung Oh
JRJinho Ryu
Jinho Ryu
Kyungho LeeKyungho Lee
Kyungho Lee
Security professionals, government agencies, and corporate organizations have found an inherent need to prevent or mitigate attacks from insider threats. Accordingly, active research on insider threat detection has been conducted to prevent and mitigate adverse effects such as leakage of valuable information that may be caused by insiders. Along with the growth of Internet-of-Things (IoT), new security challenges arise in the existing security frameworks. Attack surfaces are significantly enlarged which could cause a severe risk in terms of company insider threat management. In this work, we provide a generalization of aspects of insider threats with IoT and analyze the surveyed literature based on both private and public sources. We then examine data sources considering IoT environments based on the characteristics and the structure of IoT (perceptual, network, and application layers). The result of reviewing the study shows that using the data source of the network and application layer is more suitable than the perceptual layer in the IoT environment. We also categorized each layer’s data sources according to their features, and we investigated research objectives and methods for each category. Finally, the potential for utilization and limitations under the IoT environment are presented at the end of each layer examination.

30 July 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
HKHo-myung Kim
Ho-myung Kim
Kyungho LeeKyungho Lee
Kyungho Lee
The smart factory environment has been transformed into an Industrial Internet of Things (IIoT) environment, which is an interconnected and open approach. This has made smart manufacturing plants vulnerable to cyberattacks that can directly lead to physical damage. Most cyberattacks targeting smart factories are carried out using malware. Thus, a solution that efficiently detects malware by monitoring and analyzing network traffic for malware attacks in smart factory IIoT environments is critical. However, achieving accurate real-time malware detection in such environments is difficult. To solve this problem, this study proposes an edge computing-based malware detection system that efficiently detects various cyberattacks (malware) by distributing vast amounts of smart factory IIoT traffic information to edge servers for deep learning processing. The proposed malware detection system consists of three layers (edge device, edge, and cloud layers) and utilizes four meaningful functions (model training and testing, model deployment, model inference, and training data transmission) for edge-based deep learning. In experiments conducted on the Malimg dataset, the proposed malware detection system incorporating a convolutional neural network with image visualization technology achieved an overall classification accuracy of 98.93%, precision of 98.93%, recall of 98.93%, and F1-score of 98.92%.

10 September 2023 in Sensors
Verified
Journal Article
Open access
PDF file
Jiwon A. ChungJiwon A. Chung
Jiwon A. Chung
Kyungho LeeKyungho Lee
Kyungho Lee
Efficiently and accurately identifying fraudulent credit card transactions has emerged as a significant global concern along with the growth of electronic commerce and the proliferation of Internet of Things (IoT) devices. In this regard, this paper proposes an improved algorithm for highly sensitive credit card fraud detection. Our approach leverages three machine learning models: K-nearest neighbor, linear discriminant analysis, and linear regression. Subsequently, we apply additional conditional statements, such as “IF” and “THEN”, and operators, such as “>“ and “<“, to the results. The features extracted using this proposed strategy achieved a recall of 1.0000, 0.9701, 1.0000, and 0.9362 across the four tested fraud datasets. Consequently, this methodology outperforms other approaches employing single machine learning models in terms of recall.

29 September 2021 in Sensors
Verified
Journal Article
Open access
PDF file
KKKyoungmin Kim
Kyoungmin Kim
YSYoungsup Shin
Youngsup Shin
Jemin LeeJemin Lee
Jemin Lee
Kyungho LeeKyungho Lee
Kyungho Lee
During the past decade, mobile attacks have been established as an indispensable attack vector adopted by Advanced Persistent Threat (APT) groups. The ubiquitous nature of the smartphone has allowed users to use mobile payments and store private or sensitive data (i.e., login credentials). Consequently, various APT groups have focused on exploiting these vulnerabilities. Past studies have proposed automated classification and detection methods, while few studies have covered the cyber attribution. Our study introduces an automated system that focuses on cyber attribution. Adopting MITRE’s ATT&CK for mobile, we performed our study using the tactic, technique, and procedures (TTPs). By comparing the indicator of compromise (IoC), we were able to help reduce the false flags during our experiment. Moreover, we examined 12 threat actors and 120 malware using the automated method for detecting cyber attribution.