• Journal of the Korea Society of Computer and Information
• /
• v.18 no.5
• /
• pp.35-42
• /
• 2013

Shot boundary detection is an essential step for efficient browsing, sorting, and classification of video data. Robust shot detection method should overcome the disturbances caused by pixel brightness and object movement between frames. In this paper, two shot boundary detection methods are presented to address these problem by using segmentation, object movement, and pixel brightness. The first method is based on the histogram that reflects object movements and the morphological dilation operation that considers pixel brightness. The second method uses the pixel brightness information of segmented and whole blocks between frames. Experiments on digitized video data of National Archive of Korea show that the proposed methods outperforms the existing pixel-based and histogram-based methods.

• Journal of KIISE:Information Networking
• /
• v.36 no.3
• /
• pp.173-183
• /
• 2009

We present a real-time monitoring system for detecting anomalous network events using the entropy. The entropy accounts for the effects of disorder in the system. When an abnormal factor arises to agitate the current system the entropy must show an abrupt change. In this paper we deliberately model the Internet to measure the entropy. Packets flowing between these two networks may incur to sustain the current value. In the proposed system we keep track of the value of entropy in time to pinpoint the sudden changes in the value. The time-series data of entropy are transformed into the two-dimensional domains to help visually inspect the activities on the network. We examine the system using network traffic traces containing notorious worms and DoS attacks on the testbed. Furthermore, we compare our proposed system of time series forecasting method, such as EWMA, holt-winters, and PCA in terms of sensitive. The result suggests that our approach be able to detect anomalies with the fairly high accuracy. Our contributions are two folds: (1) highly sensitive detection of anomalies and (2) visualization of network activities to alert anomalies.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.21 no.3
• /
• pp.89-100
• /
• 2011

As the Internet usage with web browser is more increasing, the web-based malware which is distributed in websites is going to more serious problem than ever. The central type malicious website detection method based on crawling has the problem that the cost of detection is increasing geometrically if the crawling level is lowered more. In this paper, we proposed a security tool based on web browser which can detect the malicious web pages dynamically and support user's safe web browsing by stopping navigation to a certain malicious URL injected to those web pages. By applying these tools with many distributed web browser users, all those users get to participate in malicious website detection and feedback. As a result, we can detect the lower link level of websites distributed and dynamically.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.6
• /
• pp.23-31
• /
• 2022

Due to the recent outbreak of COVID-19 and an aging population and an increase in single-person households, the amount of time that household members spend doing various activities at home has increased significantly. In this study, we propose an algorithm for detecting anomalies in members of single-person households, including the elderly, based on the results of human movement and fall detection using an image sensor algorithm through home CCTV, an activity sensor algorithm using an acceleration sensor built into a smartphone, and a 2D LiDAR sensor-based LiDAR sensor algorithm. However, each single sensor-based algorithm has a disadvantage in that it is difficult to detect anomalies in a specific situation due to the limitations of the sensor. Accordingly, rather than using only a single sensor-based algorithm, we developed a fusion method that combines each algorithm to detect anomalies in various situations. We evaluated the performance of algorithms through the data collected by each sensor, and show that even in situations where only one algorithm cannot be used to detect accurate anomaly event through certain scenarios we can complement each other to efficiently detect accurate anomaly event.

• Journal of the Society of Disaster Information
• /
• v.19 no.4
• /
• pp.968-975
• /
• 2023

Purpose: We would like to confirm that the false positive rate of flames/smoke is high when detecting fires. Propose a method and dataset to recognize and classify fire situations to reduce the false detection rate. Method: Using the video as learning data, the characteristics of the fire situation were extracted and applied to the classification model. For evaluation, the model performance of Yolov8 and Slowfast were compared and analyzed using the fire dataset conducted by the National Information Society Agency (NIA). Result: YOLO's detection performance varies sensitively depending on the influence of the background, and it was unable to properly detect fires even when the fire scale was too large or too small. Since SlowFast learns the time axis of the video, we confirmed that detects fire excellently even in situations where the shape of an atypical object cannot be clearly inferred because the surrounding area is blurry or bright. Conclusion: It was confirmed that the fire detection rate was more appropriate when using a video-based artificial intelligence detection model rather than using image data.

• Convergence Security Journal
• /
• v.24 no.2
• /
• pp.19-29
• /
• 2024

A crypto-jacking attack is an attack that infringes on the availability of users by stealing computing resources required for cryptocurrency mining. The target of the attack is gradually diversifying from general desktop or server environments to cloud environments. Therefore, it is essential to apply a crypto-minor detection technique suitable for various computing environments. However, since the existing detection methodologies have only been detected in a specific environment, comparative analysis has not been properly performed on the methodologies that can be applied to each environment. Therefore, in this study, classification criteria for conventional crypto-minor detection techniques are established, and a complex and integrated detection framework applicable to the cloud environment is presented through in-depth comparative analysis of existing crypto-minor detection techniques based on different experimental environments and datasets.

• Review of KIISC
• /
• v.15 no.2
• /
• pp.74-82
• /
• 2005

오늘날 네트워크 보안 기술은 해커의 침입 탐지 및 제어, 분산 서비스 거부 공격의 방지 등 많은 분야에서 발전하여 왔다. 그러나, 최근 많은 문제를 발생시키면서 등장한 인터넷 웜은 기존의 네트워크 보안 장비들을 무력화시키며 인터넷 상에 연결된 많은 호스트들을 감염시키고 동시에 네트워크 자원을 소모시켜 버렸다. 실상 초기의 웜은 작은 규모의 네트워크에서 퍼지는 정도 일뿐 심각한 피해를 주는 경우는 거의 없었고 따라서 이에 대해서 심각한 대비책 등을 생각하지는 않았다. 그러나 2001년 발생한 CodeRed 웜은 인터넷에 연결된 많은 컴퓨터들을 순식간에 감염시켜 많은 경제적, 물질적 피해를 발생시켰고, 그 이후 2003년 1월에 발생한 Stammer 웜은 10분이라는 짧은 순간 안에 75000 여대 이상의 호스트를 감염시키고 네트워크 자체를 마비시켰다. 특히 Stammer 월은 국내에서 많은 피해를 유발시켰기에 더더욱 유명하다. 명절 구정과 맞물려 호황을 누리던 인터넷 쇼핑 몰과, 인터넷 금융 거래를 수행하던 은행 전산소 등을 일시에 마비시켜 버리면서 경제적으로도 실질적인 막대한 피해를 우리에게 주었다. 이런 웜을 막기 위해서 많은 보안 업체 및 연구소들이 나서고 있으나, 아직은 사전에 웜의 피해를 막을만한 확실한 대답을 얻지 못하고 있다. 본 논문에서는, 현재 수행하고 있는 여러 웜의 탐지기법에 대해서 조사한 결과를 설명하고, 이어서 본 연구소에서 수행하고 있는 웜의 탐지 기법에 대해서 설명하고 간단한 탐지 결과를 보일 것이다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.27 no.6
• /
• pp.1385-1395
• /
• 2017

This paper aims to develop an IDS (Intrusion Detection System) that takes into account class imbalanced datasets. For this, we first built a set of training data sets from the Kyoto 2006+ dataset in which the amounts of normal data and abnormal (intrusion) data are not balanced. Then, we have run a number of tests to evaluate the effectiveness of machine learning techniques for detecting intrusions. Our evaluation results demonstrated that the Random Forest algorithm achieved the best performances.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.830-832
• /
• 2018

사람의 출입이 없는 폐쇄된 돈사에서 돼지에 대한 자동 감시 시스템에 관한 연구는 돼지의 움직임을 탐지 및 추적함으로써 돼지의 상태를 실시간으로 분석하기 위해 진행되고 있다. 그러나 돈사 내 감시 카메라를 통한 돼지의 움직임 탐지 및 추적은 여러 환경적/구조적인 제약으로 인하여 문제점이 발생한다. 특히, 돈사 내 사료통 등과 같은 고정 구조물에 의하여 돼지를 정확히 탐지할 수 없는 문제가 있다. 본 논문에서는 이러한 고정 구조물에 가려진 돼지 영역을 탐지하기 위하여 먼저 구조물의 영역을 설정 후 제거하고, 돼지의 가려진 영역을 가려지지 않은 영역 정보를 이용하여 보정하는 픽셀 보간 기법을 제안한다. 실험 결과, 구조물에 의하여 가려진 돼지의 영역이 적절히 보간되었고, 실시간으로 처리(평균 보간 수행 시간은 2~3 msec)됨을 확인하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1431-1434
• /
• 2015

24시간 모니터링 환경에서 돈사 내 개별 돼지들의 상태를 자동으로 탐지하는 연구는 효율적인 돈사 관리 측면에서 중요한 이슈로 떠오르고 있다. 특히 돼지 호흡기 질병은 전염성이 매우 강하여, 막대한 경제적 손실을 최소화하기 위해서는 조기에 탐지하는 것이 매우 중요하다. 본 논문에서는 마이크를 통한 소리 정보뿐 아니라 카메라를 통한 영상 정보를 동시에 활용하여 호흡기 질병에 걸린 개별 돼지를 조기에 탐지하는 방법을 제안한다. 즉, 돈사의 천장에 설치된 마이크로부터 호흡기 질병에 걸린 소리 정보를 먼저 탐지한 후 카메라로부터 획득된 영상 정보의 MHI 분석을 수행하여 호흡기 질병에 걸린 돼지를 특정한다. 실험결과, 소리와 영상 정보를 동시에 활용하는 제안 방법을 이용하여 호흡기 질병에 걸린 돼지를 특정할 수 있음을 확인하였다.