• Proceedings of the Korean Geotechical Society Conference
• /
• 2002.10a
• /
• pp.27-43
• /
• 2002

This paper described two case studies on large scale failure of cutting slope. The kind of rock in both sites predominated limestone and shale respectively. These cutting slopes located in northern area of Gyongbug Province are composed of very complicated and various rock mass. Geological characteristics, causes of failure, proceeding of security diagnose, maintenance method etc. of two sites were carried out to check the cutting slope stability and to provide reasonable maintenance method. This paper may provide the useful data for engineers related with design and construction of large cutting slope.

• Journal of Digital Convergence
• /
• v.16 no.6
• /
• pp.205-212
• /
• 2018

This Study aims to propose a new information security governance model design method for streamlining security governance at national strategic level. The research method of this study is to diagnose our operational experience and to derive a new model design method. In the meantime, national information security activities were perceived to be focused on knowledge transfer, and motivation of activities and securing of executive power were weak. As a result, security blind spots and frequent occurrence of large security incidents have become unresolved challenges. National cyber security governance should be grouped together as a whole systematically from the upper policy to the lower level of performance under the responsibility of the national leader. Based on this approach, this study presented the comprehensive framework of Korean security governance model and embodied it into four architectural designs such as vision, goal, process, and performance, thus deriving the foundation for future national governance model design. Further research is needed to diagnose problems in life cycle flow, security policies based on environmental changes, and new frameworks in which all subjects participate.

• International Journal of Computer Science & Network Security
• /
• v.21 no.11
• /
• pp.165-170
• /
• 2021

Discrete event systems interact with the external environment to decide which action plan is adequate. Some of these interactions are not predictable in the modelling phase and require consequently an adaptation of the system to the metamorphosed behavior of the environment. One of the challenging issues is to guarantee safety behavior when failures tend to derive the system from normal status. In this paper we propose a framework to combine diagnose technique with adaptive control to avoid unsafe sate an maintain the normal behavior as long as possible.

• KEPCO Journal on Electric Power and Energy
• /
• v.6 no.4
• /
• pp.399-404
• /
• 2020

There are many attempts to apply AI technology to diagnose facilities or improve the work efficiency of the power industry. The emergence of new machine learning technologies, such as deep learning, is accelerating the digital transformation of the power sector. The problem is that traditional power systems face security risks when adopting state-of-the-art AI systems. This adoption has convergence characteristics and reveals new cybersecurity threats and vulnerabilities to the power system. This paper deals with the security measures and implementations of the power system using machine learning. Through building a commercial facility operations forecasting system using machine learning technology utilizing power big data, this paper identifies and addresses security vulnerabilities that must compensated to protect customer information and power system safety. Furthermore, it provides security guidelines by generalizing security measures to be considered when applying AI.

• Journal of IKEEE
• /
• v.25 no.4
• /
• pp.672-678
• /
• 2021

New malware continues to increase and become advanced by every year. Although various studies are going on executable files to diagnose malicious codes, it is difficult to detect attacks that internalize malicious code threats in emails by exploiting non-executable document files, malicious URLs, and malicious macros and JS in documents. In this paper, we introduce a method of analyzing malicious code for email security through proactive detection and blocking of malicious email attacks, and propose a method for determining whether a non-executable document file is malicious based on AI. Among various algorithms, an efficient machine learning modeling is choosed, and an ML workflow system to diagnose malicious code using Kubeflow is proposed.

• International journal of advanced smart convergence
• /
• v.10 no.4
• /
• pp.22-29
• /
• 2021

For web application vulnerability diagnosis, from the development stage to the operation stage, it is possible to stably operate the web only when there is a policy that is commonly applied to each task through diagnosis of vulnerabilities, removal of vulnerabilities, and rapid recovery from web page damage. KISA presents 28 evaluation items for technical vulnerability analysis of major information and communication infrastructure. In this paper, we diagnose the vulnerabilities in the automobile goods shopping mall website and suggest security measures according to the vulnerabilities. As a result of diagnosing 28 items, major vulnerabilities were found in three items: cross-site scripting, cross-site request tampering, and insufficient session expiration. Cookie values were exposed on the bulletin board, and personal information was exposed in the parameter values related to passwords when personal information was edited. Also, since the session end time is not set, it was confirmed that session reuse is always possible. By suggesting security measures according to these vulnerabilities, the discovered security threats were eliminated, and it was possible to prevent breaches in web applications and secure the stability of web services.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.347-350
• /
• 2016

Analysis of vulnerability of the software for risk. The weakness of the software material, the importance of strengthening security in accordance with financial damage occurred is emerging. There is a potential risk factor not only from the case, the manufacturing to use the software company that appropriate to use a software business and personal risk of loss to size.In this paper due to diagnose and vulnerabilities in software, diagnosis, the curriculum and to cultivate a diagnostic guide, and security vulnerabilities in software.Proposal system for increased.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2009.10a
• /
• pp.291-292
• /
• 2009

• International Journal of Computer Science & Network Security
• /
• v.22 no.12
• /
• pp.98-106
• /
• 2022

A condition of the retina known as hypertensive retinopathy (HR) is connected to high blood pressure. The severity and persistence of hypertension are directly correlated with the incidence of HR. To avoid blindness, it is essential to recognize and assess HR as soon as possible. Few computer-aided systems are currently available that can diagnose HR issues. On the other hand, those systems focused on gathering characteristics from a variety of retinopathy-related HR lesions and categorizing them using conventional machine-learning algorithms. Consequently, for limited applications, significant and complicated image processing methods are necessary. As seen in recent similar systems, the preciseness of classification is likewise lacking. To address these issues, a new CAD HR-diagnosis system employing the advanced Deep Dense CNN Learning (DD-CNN) technology is being developed to early identify HR. The HR-diagnosis system utilized a convolutional neural network that was previously trained as a feature extractor. The statistical investigation of more than 1400 retinography images is undertaken to assess the accuracy of the implemented system using several performance metrics such as specificity (SP), sensitivity (SE), area under the receiver operating curve (AUC), and accuracy (ACC). On average, we achieved a SE of 97%, ACC of 98%, SP of 99%, and AUC of 0.98. These results indicate that the proposed DD-CNN classifier is used to diagnose hypertensive retinopathy.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.6
• /
• pp.1585-1594
• /
• 2018

In recent years The importance of information security management for securing information collection and analysis, production and distribution is increasing. Companies are assured of confidence in information security through authentication of information Security Management System. However, level assessment and use of domains that make up the management system is limited. On the other hand, the security maturity model is able to diagnose the level of information protection of the enterprise step by step. It is also possible to judge the area to be improved urgently. It is a tool to support goal setting according to the characteristics and level of company. In this paper, C2M2, which is an example of security maturity model, is compared and analyzed with Korea Information Security Management System certification. Benchmark the model to check the level of information security management and derive the priority among the items that constitute the detailed area of information security measures of ISMS certification. It also look at ways to check the level of information security management step by step.