• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.4
• /
• pp.701-713
• /
• 2021

Race Condition is a vulnerability in which two or more processes input or manipulate a common resource at the same time, resulting in unintended results. This vulnerability can lead to problems such as denial of service, elevation of privilege. When a vulnerability occurs in software, the relevant information is documented, but often the cause of the vulnerability or the source code is not disclosed. In this case, analysis at the binary level is necessary to detect the vulnerability. This paper aims to detect the Time-Of-Check Time-Of-Use (TOCTOU) Race Condition vulnerability of UNIX kernel-based File System at the binary level. So far, various detection techniques of static/dynamic analysis techniques have been studied for the vulnerability. Existing vulnerability detection tools using static analysis detect through source code analysis, and there are currently few studies conducted at the binary level. In this paper, we propose a method for detecting TOCTOU Race Condition in File System based on Control Flow Graph and Call Graph through Binary Analysis Platform (BAP), a binary static analysis tool.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.557-559
• /
• 2022

The use of open source has the advantage that the development environment is convenient and maintenance is easier, but there is a limitation in that it is easy to be exposed to vulnerabilities from a security point of view. In this regard, the LOG4J vulnerability, which is an open source logging library widely used in Apache, was recently discovered. Currently, the risk of this vulnerability is at the 'highest' level, and developers are using it in many systems without being aware of such a problem, so there is a risk that hacking accidents due to the LOG4J vulnerability will continue to occur in the future. In this paper, we analyze the LOG4J vulnerability in detail and propose a SNORT detection policy technology that can detect vulnerabilities more quickly and accurately in the security control system. Through this, it is expected that in the future, security-related beginners, security officers, and companies will be able to efficiently monitor and respond quickly and proactively in preparation for the LOG4J vulnerability.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.11
• /
• pp.1720-1728
• /
• 2022

The industrial 4.0 era has been opened with the development of artificial intelligence technology, and the realization of smart farms incorporating ICT technology is receiving great attention in the livestock industry. Among them, the quality management technology of livestock products and livestock operations incorporating computer vision-based artificial intelligence technology represent key technologies. However, the insufficient number of livestock image data for artificial intelligence model training and the severely unbalanced ratio of labels for recognizing a specific defective state are major obstacles to the related research and technology development. To overcome these problems, in this study, combining oversampling and adversarial case generation techniques is proposed as a method necessary to effectively utilizing small data labels for successful defect detection. In addition, experiments comparing performance and time cost of the applicable techniques were conducted. Through experiments, we confirm the validity of the proposed methods and draw utilization strategies from the study results.

• Journal of Korean Institute of Industrial Engineers
• /
• v.38 no.3
• /
• pp.191-197
• /
• 2012

One-class classification (OCC) is one of the recent growing areas in data mining and pattern recognition. In the present study we examine a k-nearest neighbors data description (kNNDD) algorithm, one of the OCC algorithms widely used. In particular, we propose to use nonparametric estimation methods to determine the threshold of the kNNDD algorithm. A simulation study has been conducted to explore the characteristics of the proposed approach and compare it with the existing approach that determines the threshold. The results demonstrate the usefulness and flexibility of the proposed approach.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.35 no.2
• /
• pp.71-88
• /
• 2010

A density-based outlier detection such as an LOF (Local Outlier Factor) tries to find an outlying observation by using density of its surrounding space. In spite of several advantages of a density-based outlier detection method, the computational complexity of outlier detection has been one of major barriers in its application. In this paper, we present an LOF algorithm that can reduce computation time of a density based outlier detection algorithm. A kd-tree indexing and approximated k-nearest neighbor search algorithm (ANN) are adopted in the proposed method. A set of experiments was conducted to examine performance of the proposed algorithm. The results show that the proposed method can effectively detect local outliers in reduced computation time.

• Journal of Korean Institute of Industrial Engineers
• /
• v.38 no.1
• /
• pp.17-24
• /
• 2012

We address some potential problems with the existing procedures of outlier detection in time series. Also we propose modifications in estimating model parameters and outlier effects in order to reduce the number of tests and to increase the detection accuracy. Experiments with some artificial data sets show that the proposed procedure significantly reduces the number of tests and enhances the accuracy of estimated parameters as well as the detection power.

• Journal of Korean Institute of Industrial Engineers
• /
• v.39 no.2
• /
• pp.82-89
• /
• 2013

Novelty detection (ND) is an effective technique that can be used to determine whether a future observation is normal or not. In the present study we propose a novelty detection algorithm that can handle a situation where the distributions of target (normal) observations are inhomogeneous. A simulation study and a real case with the TFT-LCD process demonstrated the effectiveness and usefulness of the proposed algorithm.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2004.03a
• /
• pp.203-208
• /
• 2004

NDVI (Normalized Difference Vegetation Index)는 식생의 건강상태 및 농작물 생산량 추정등에 효과적인 식생지수로, 20년 이상 축적된 MOAA NDVI data의 경우, 식생의 시기적, 계절적 변화탐지가 가능해져 이를 바탕으로 한 가뭄지수들이 개발되어 가뭄 모니터링에 사용되어지고 있다 지난 2001년, 한반도는 기상관측 이래 90년만의 강수량 최저치를 기록하여 전국적인 대 가뭄의 피해를 입었으며, 특히 북한은 유엔이 선정한 가뭄에 가장 취약한 국가로 그로 인한 식량난이 더욱 악화되고 있어 가뭄에 대한 정보는 필수적이라 할 수 있다. 이에 본 연구에서는 1994～2002년의 식물 생장기(growing season : 3～10월)동안 NDVI 10일 최대값 합성영상 (10-day maximum composite data)을 사용하여 남북한으로 나누어진 한반도를 대상으로 각각의 식생현황을 파악 및 비교하고, 산림, 농지, 도시지역별로 NDVI와 가뭄의 주원인인 강수량과의 상관관계로 그 효용성을 분석하였다. 그 결과, NDVI는 1～2개월 전 강수량의 영향이 가장 컸으며, 특히 농지지역에서의 상관계수가 높게 나타났다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.683-685
• /
• 2018

본 논문은 도로에서의 객체탐지를 위한 딥러닝(deep learning) 데이터셋을 자동으로 생성, 분류하는 시스템을 제안한다. 시스템의 작동 과정은 크게 두 가지이다. 먼저 딥러닝을 활용하여 촬영된 영상에 존재하는 객체를 검출한다. 이때, 실시간으로 하는 방법과 레코딩된 영상을 다루는 방법 두 가지가 있다. 다음으로 검출된 객체 중 예측 값(scroe)가 임계치 이상인 객체의 위치와 종류를 파일로 저장한다. 이 시스템은 차량 전방 카메라 위치에 장착된 웹캠을 이용해 영상을 취득하고 임베디드 보드인 TX2 board를 이용해 데이터 셋을 생성한다. 매트랩의 image labeler app과 비교를 통해 보다 적은 시간비용으로 데이터셋을 생성해 냄을 확인하였다.

• Journal of Korea Multimedia Society
• /
• v.24 no.9
• /
• pp.1242-1250
• /
• 2021

Detection of outliers deviating normal data distribution in high dimensional data is an important technique in many application areas. In this paper, a distance-based outlier detection method using landmarks in high dimensional data is proposed. Given normal training data, the k-means clustering method is applied for the training data in order to extract the centers of the clusters as landmarks which represent normal data distribution. For a test data sample, the distance to the nearest landmark gives the outlier score. In the experiments using high dimensional data such as images and documents, it was shown that the proposed method based on the landmarks of one-tenth of training data can give the comparable outlier detection performance while reducing the time complexity greatly in the testing stage.