• Journal of Convergence for Information Technology
• /
• v.8 no.6
• /
• pp.209-215
• /
• 2018

In this paper, we propose a method to detect and block Meltdown malicious code which is increasing rapidly using dynamic sandbox tool. Although some patches are available for the vulnerability of Meltdown attack, patches are not applied intentionally due to the performance degradation of the system. Therefore, we propose a method to overcome the limitation of existing signature detection method by using machine learning method for infrastructures without active patches. First, to understand the principle of meltdown, we analyze operating system driving methods such as virtual memory, memory privilege check, pipelining and guessing execution, and CPU cache. And then, we extracted data by using Linux strace tool for detecting Meltdown malware. Finally, we implemented a decision tree based dynamic detection mechanism to identify the meltdown malicious code efficiently.

• Korean Journal of Construction Engineering and Management
• /
• v.20 no.4
• /
• pp.3-12
• /
• 2019

VE analysis is a method to secure definite functions and performance by defining user's various requirements clearly and propose alternatives to reduce cost. However, the present domestic VE project has difficulty in defining design function analysis clearly due to time constraints as well as difficulty in effective and efficient communication between project stakeholder. Domestic results of VE were largely focused on reducing cost while maintaining the functions of the existing facility. Therefore, this study aims to secure the optimal functions for users according to the original intent of user requirements through QFD-VE model which project VE participants can make collective and cooperative decision making. QFD-VE is a technique that first, it can make collaborative decision making in defining and modifying of design function and setting the importance of requirement function. Second, it allow project VE participants to check design interference and conflict between neighbor systems. This study also provided a mathematical model for implementing the computer system using QFD-VE in the future.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.6
• /
• pp.1081-1090
• /
• 2022

The face recognition model is used for identity recognition of smartphones, providing convenience to many users. As a result, the security review of the DNN model is becoming important, with adversarial attacks present as a well-known vulnerability of the DNN model. Adversarial attacks have evolved to decision-based attack techniques that use only the recognition results of deep learning models to perform attacks. However, existing decision-based attack technique[14] have a problem that requires a large number of queries when generating adversarial examples. In particular, it takes a large number of queries to approximate the gradient. Therefore, in this paper, we propose a method of generating adversarial examples using orthogonal space sampling and dimensionality reduction sampling to avoid wasting queries that are consumed to approximate the gradient of existing decision-based attack technique[14]. Experiments show that our method can reduce the perturbation size of adversarial examples by about 2.4 compared to existing attack technique[14] and increase the attack success rate by 14% compared to existing attack technique[14]. Experimental results demonstrate that the adversarial example generation method proposed in this paper has superior attack performance.

• Ecology and Resilient Infrastructure
• /
• v.7 no.4
• /
• pp.256-261
• /
• 2020

Roadside non-point pollution reduction facilities are classified as infiltration, vegetation, reservoir, and wetland types based on their respective pollution reduction mechanisms. However, without a detailed analysis of the road and traffic conditions it is very difficult for civil engineers to determine which category of pollution reduction facility is best suited to their planning requirements. To address this issue, we propose a new decision-making method for the selection of roadside non-point pollution reduction facilities. The principal factors informing the proposed decision-making methods are the road characteristics, including location, structure, number of lanes, and traffic volume. As a result of the study, a total of new pollution reduction plans were developed, with their selection conditions and the corresponding applicable facilities established. The effectiveness of the proposed pollution reduction schemes was demonstrated for roads in Kyounggi-do, providing a valuable basis for future pollution reduction plans.

• Journal of the Korean Society for Railway
• /
• v.11 no.1
• /
• pp.45-53
• /
• 2008

With the growing international consensus regarding sustainable development of transportation, the plan of transportation infrastructure needs to meet various requirements toward enhancing environmental conditions. Accordingly, the upcoming long-term plan of high-speed rail network has to be reflecting the sustainability of transportation systems. In this paper, we demonstrate an application of methodologies based on multi-attribute utility theory for determining priorities of sustainable high-speed rail investment. The proposed methodologies identify indicators for sustainable transportation systems such as economic, environmental, and social ones and then, evaluate priority for planning a long-term sustainable high-speed rail network by comparing the relative importance among indicators. This will help transportation agencies to prioritize high-speed rail investment toward sustainable transportation systems.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.9 no.2
• /
• pp.544-549
• /
• 2008

National Education Information System (NEIS) is an ambitious reform project in the field of education, which is launched mainly by government initiative and is to link administrational work of between schools and their senior administration offices via internet. NEIS is introduced to lighten the teachers' overburden, to standardize the work process and to bring better quality education to each classroom and make it possible for those involved in education to resolve any related educational problem on line. This paper aims to construct a hierarchy model consisting of key factors such as administrative and technological factors for the effective use of NEIS and to evaluate the relative importance among key factors using multiple decision-making technique. Eventually, the analysis results can be utilized to develop the future improvement strategy of NEIS and to satisfy the users.

• Journal of KIISE:Software and Applications
• /
• v.29 no.3
• /
• pp.156-166
• /
• 2002

Decision tree induction is a kind of useful machine learning approach for extracting classification rules from a set of feature-based examples. According to the partitioning style of the feature space, decision trees are categorized into univariate decision trees and multivariate decision trees. Due to observation error, uncertainty, subjective judgment, and so on, real-world data are prone to contain some errors in their feature values. For the purpose of making decision trees robust against such errors, there have been various trials to incorporate fuzzy techniques into decision tree construction. Several researches hove been done on incorporating fuzzy techniques into univariate decision trees. However, for multivariate decision trees, few research has been done in the line of such study. This paper proposes a fuzzy decision tree induction method that builds fuzzy multivariate decision trees named fuzzy oblique decision trees, To show the effectiveness of the proposed method, it also presents some experimental results.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2009.05a
• /
• pp.1754-1758
• /
• 2009

본 연구에서는 개정된 하천법에 의거하여 지방하천들 중에서 국가하천으로 지정하기에 적합한 하천들을 선별하여 이들의 관리등급을 조정하기 위한 방법론을 개발하였다. 대상 하천들 사이의 관리등급조정에 대한 우선순위를 결정하기 위하여 다기준의사결정법을 적용하였다. 개발된 하천평가지수에서는 세부기준을 하천중요도, 하천관리상태, 하천관리능력으로 구분하였으며, 지형 및 수문학적, 사회 및 경제적, 환경적 측면에서 각 세부기준들을 평가할 수 있는 지표들을 선정하였다. 또한, 수자원 분야 전문가들을 대상으로 설문조사를 실시하고 계층적 분석기법을 사용하여 평가기준들과 평가지표들의 상대적 중요도를 결정하였다. 국가하천지정 우선순위는 대상하천의 등급을 8개로 구분하고 각 등급 내에서 하천평가지수의 상대적 크기를 비교하여 결정하였다.

• Journal of Korea Water Resources Association
• /
• v.46 no.10
• /
• pp.977-987
• /
• 2013

This study aims to develop a multiple criteria decision making (MCDM) approach for flood vulnerability assessment which considers uncertainty. The flood vulnerability assessment procedure consists of three steps: (1) use the Delphi process to determine the criteria and their corresponding weights-the adopted criteria represent the social, economic, and environmental circumstances related to floods, (2) construct a fuzzy data matrix for the flood vulnerability criteria using fuzzification and standardization, and (3) set priorities based on the number of assessed vulnerabilities. This study uses a modified fuzzy TOPSIS method based on ${\alpha}$-level sets which considers various uncertainties related to weight derivation and crisp data aggregation. Further, Spearman's rank correlation analysis is used to compare the rankings obtained using the proposed method with those obtained using fuzzy TOPSIS with fuzzy data, TOPSIS, and WSM methods with crisp data. The fuzzy TOPSIS method based on ${\alpha}$-cut level sets is found to have a higher correlation rate than the other methods, and thus, it can reduce the difference of the rankings which uses crisp and fuzzy data. Thus, the proposed flood vulnerability assessment method can effectively support flood management policies.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.2
• /
• pp.263-270
• /
• 2010

Data mining is the process of sorting through large amounts of data and picking out useful information. An important goal of data mining is to discover, define and determine the relationship between several variables. Association rule mining is an important research topic in data mining. An association rule technique finds the relation among each items in massive volume database. Association rule technique consists of two steps: finding frequent itemsets and then extracting interesting rules from the frequent itemsets. Some interestingness measures have been developed in association rule mining. Interestingness measures are useful in that it shows the causes for pruning uninteresting rules statistically or logically. This paper explores some problems for two interestingness measures, confidence and net confidence, and then propose a decision process for right association rule generation using these interestingness measures.