• Journal of KIISE
• /
• v.43 no.12
• /
• pp.1325-1333
• /
• 2016

Software classification has several applications such as copyright infringement detection, malware classification, and software automatic categorization in software repositories. It can be also employed by software filtering systems to prevent the transmission of illegal software. If illegal software is identified by measuring software similarity in software filtering systems, the average number of comparisons can be reduced by shrinking the search space. In this study, we focused on the classification of Windows executables using API call information and machine learning. We evaluated the classification performance of machine learning-based classifier according to the refinement method for API information and machine learning algorithm. The results showed that the classification success rate of SVM (Support Vector Machine) with PolyKernel was higher than other algorithms. Since the API call information can be extracted from binary executables and machine learning-based classifier can identify tampered executables, API call information and machine learning-based software classifiers are suitable for software filtering systems.

• Fire Science and Engineering
• /
• v.23 no.2
• /
• pp.13-19
• /
• 2009

This study is related with fire risk assessment for occupant of the area adjacent to not enclosed atrium through the computer modeling and application of enhanced fire protection systems depending on the result. Fire scenario is intended to evaluate the impact of a fire from atrium base within the corridor adjacent to the atrium and to compare with egress time depending on the warning system. The major purpose of this study is to figure out fire life safety for occupant adjacent to atrium through the computer simulation and to suggest alternative option in case the occupant safety is not guaranteed.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.23 no.2
• /
• pp.231-242
• /
• 2013

Recently, automated software testing methods such as fuzzing have been researched to find software vulnerabilities. The purpose of fuzzing is to disclose software vulnerabilities by providing a software with malformed data. In order to increase the probability of vulnerability discovery by fuzzing, we must solve the test suite reduction problem because the probability depends on the test case quality. In this paper, we propose a new method to solve the test suite reduction problem which is suitable for the long test case such as file. First, we suggested the length of test case as a measure in addition to old measures such as coverage and redundancy. Next we designed a test suite reduction algorithm using the new measure. In the experimental results, the proposed algorithm showed better performance in the size and length reduction ratio of the test suite than previous studies. Finally, results from an empirical study suggested the viability of our proposed measure and algorithm for file fuzzing.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.20 no.2
• /
• pp.50-59
• /
• 2006

In this paper, We are going to propose the fire protection system using CAN(Controller Area Network). The larger, higher and deeper buildings an, the more dangerous people are when fire happens. We should be aware of the problems of prior fire protection system. Therefore, we construct the embedded system based on CAN communication that is capable of N to N communication, and build independent fire protection system. If the fire is occurred on the building, the problem is that how fast we can detect the fire and put it on by using available system, this is major factor that reduces damage of our wealth. Therefore in this studies, We would like to design more stable system than current system. This system is based on CAN communication which is available N to N communication constructs and designed to compensate for each fault, so that our aim is to reduce the wires of system, cost of installation and to suppose future type fire protection system.

• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.2
• /
• pp.226-230
• /
• 2008

Prefetching is one of widely used techniques to improve performance of I/O. But it has been reported that prefetching can bring adverse result on some reference pattern. This paper proposes a prefet-ching frame that can be adopted on existing prefetching techniques simply. The frame called IPRP (Improving Prefetching Effects by Exploiting Reference Patterns) and detects reference patterns online and control pre-fetching upon the characteristics of the detected pattern. In our experiment, we adopted IPRP on Linux read-ahead prefetching. IPRP could prevent adverse result clearly when Linux read-ahead prefetching increases total execution time about $40%{\sim}70%$. When Linux read-ahead prefetching could bring some benefit, IPRP with read- ahead performed similar or slightly better benefit on execution time. With this result we could see our IPRP can complement and improve legacy prefetching techniques efficiently.

• Korean Journal of Cognitive Science
• /
• v.20 no.4
• /
• pp.535-554
• /
• 2009

Information collected on mobile devices might be utilized to support user's memory, but it is difficult to effectively retrieve them because of the enormous amount of information. In order to organize information as an episodic approach that mimics human memory for the effective search, it is required to detect important event like landmarks. For providing new services with users, in this paper, we propose the prediction model to find landmarks automatically from various context log information based on attributed Bayesian networks. The data are divided into daily and weekly ones, and are categorized into attributes according to the source, to learn the Bayesian networks for the improvement of landmark prediction. The experiments on the Nokia log data showed that the Bayesian method outperforms SVMs, and the proposed attributed Bayesian networks are superior to the Bayesian networks modelled daily and weekly.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.27 no.11
• /
• pp.82-88
• /
• 2013

It is important to give lightning warning prior to a cloud-to-ground (CG) discharge within an Area of Concern (AOC) because most of lightning damage and victim are usually occurred by the first lightning in the AOC. The aim of this study is to find the optimal operation conditions of the automated lightning warning systems in order to make the best use of the available data. In this paper, the test-operated results of the automated lightning alert and risk management system (ALARM) based on detections of CG discharge and eletrostatic field and optimized at probability of lightning have been described. It was possible to obtain the following warning performance parameters: probability of detection (POD), false alarm ratio (FAR), probability of lightning (POL) and failure-to-warn rate (FTW). The data obtained from trial operation for 5months were not sufficient but the first analysis of domestic lightning warning was carried out. We have observed that the evaluated statistical results through trial operation depend on the various factors such as analysis methods and criteria, topographical conditions, etc. Also we suggest some methods for improvement of POL and POD including the finding of the optimal electric field threshold level to be used, based on the high values of FAR and FTW found in this work.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.23 no.3
• /
• pp.501-514
• /
• 2013

A grouping process through the similarity comparison is required to effectively classify and respond a malicious code. When we have a use of the past similarity criteria to be used in the comparison method or properties it happens a increased problem of false negatives and false positives. Therefore, in this paper we apply to choose variety of properties to complement the problem of behavior analysis on the heuristic-based of 2nd step in malicious code auto analysis system, and we suggest a similarity comparison method applying AHP (analytic hierarchy process) for properties weights that reflect the decision-making technique. Through the similarity comparison of malicious code, configured threshold is set to the optimum point between detection rates and false positives rates. As a grouping experiment about unknown malicious it distinguishes each group made by malicious code generator. We expect to apply it as the malicious group information which includes a tracing of hacking types and the origin of malicious codes in the future.

• Journal of Korea Multimedia Society
• /
• v.14 no.10
• /
• pp.1303-1310
• /
• 2011

This paper proposes the design of 3-party negotiation protocol for the security of self_organized storage which consists of the owner node possessing data, the holder node holding the owner's data and the verification node verifying the data of the holder node on infra-cloud environment. The proposed security technique delegating the data verification of the holder node to the verification node increases the efficiency of the self-organized storage. In addition, the encrypt key and certification of the storage created by EC-DH algorithm enhances the security much more. Also, when the self-organized storage is composed, the security technique not only prevents external flooding attack by setting a certification key among three parties, but also prevents internal flooding attack by restricting the number of verification nodes. And The replay attack which can occur in the step of verification is automatically detected by using the created seed value whenever the verification is requested.

• The KIPS Transactions:PartB
• /
• v.17B no.4
• /
• pp.263-274
• /
• 2010

To provide context-aware music recommendation service, first of all, we need to catch music mood that a user prefers depending on his situation or context. Among various music characteristics, music mood has a close relation with people‘s emotion. Based on this relationship, some researchers have studied on music mood detection, where they manually select a representative segment of music and classify its mood. Although such approaches show good performance on music mood classification, it's difficult to apply them to new music due to the manual intervention. Moreover, it is more difficult to detect music mood because the mood usually varies with time. To cope with these problems, this paper presents an automatic method to classify the music mood. First, a whole music is segmented into several groups that have similar characteristics by structural information. Then, the mood of each segments is detected, where each individual's preference on mood is modelled by regression based on Thayer's two-dimensional mood model. Experimental results show that the proposed method achieves 80% or higher accuracy.