• Journal of the Korea Society of Computer and Information
• /
• v.26 no.9
• /
• pp.49-55
• /
• 2021

In this paper, an enhanced 2-stage vehicle license plate detection scheme using object segmentation is proposed to detect accurately the rotated license plates due to the inclined photographing angles in real-road situations. With the previous 3-stage vehicle license plate detection pipeline model, the detection accuracy is likely decreased as the license plates are declined. To resolve this problem, we propose an enhanced 2-stage model by replacing the frontal two processing stages which are for detecting vehicle area and vehicle license plate respectively in only rectangular shapes in the previous 3-stage model with one step to detect vehicle license plate in arbitrarily shapes using object segmentation. According to the comparison results in terms of the detection accuracy of the proposed 2-stage scheme and the previous 3-stage pipeline model against the rotated license plates, the accuracy of the proposed 2-stage scheme is improved by up to about 20% even though the detection process is simplified.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.2
• /
• pp.454-460
• /
• 2000

In this paper, an architecture is suggested which efficiently detects intrusions in network environments. In the architecture, the Blackboardbased agent coordinates opinions of several independent agents which are performing unique functions, by resolving conflicts and reconfirming notices of intrusion. In the simulation, it was found that conventional agents judge simple resource access activities as 'intrusion' while blakcboard-based agent reserves the judgement until additional information confirms notices of independent agents. Reconfirmation process based on additional questioning will roduce positive errors.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.78-81
• /
• 2021

Through the smart factory construction project, sensors can be installed in manufacturing production facilities and various process data can be collected in real time. Through this, research on real-time facility anomaly detection is being actively conducted to reduce production interruption due to facility abnormality in the manufacturing process. In this paper, to detect abnormalities in production facilities, the manufacturing data was applied to deep learning models Autoencoder(AE), VAE(Variational Autoencoder), and AAE(Adversarial Autoencoder) to derive the results. Manufacturing data was used as input data through a simple moving average technique and preprocessing process, and performance analysis was conducted according to the window size of the simple movement average technique and the feature vector size of the AE model.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.4
• /
• pp.963-974
• /
• 2018

With the growing interest in cryptocurrency such as bitcoin, the blockchain technology has attracted much attention in various applications as a distributed security platform with excellent security. However, Cryptojacking, an attack that hijack other computer resources such as CPUs, has occured due to vulnerability to the Cryptomining process. In particular, browser-based Cryptojacking is considered serious because attacks can occur only by visiting a Web site without installing it on a visitor's PC. The current Cryptojacking detection system is mostly signature-based. Signature-based detection methods have problems in that they can not detect a new Cryptomining code or a modification of existing Cryptomining code. In this paper, we propose a Cryptojacking detection solution using a dynamic analysis-based that uses a headless browser to detect unknown Cryptojacking attacks. The proposed dynamic analysis-based Cryptojacking detection system can detect new Cryptojacking site that cannot be detected in existing signature-based Cryptojacking detection system and can detect it even if it is called or obfuscated by bypassing Cryptomining code.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10c
• /
• pp.595-597
• /
• 2002

현재 인터넷의 발달에 인한 다양한 공격의 가능성의 이유로 침입 탐지 시스템(IDsystem, IDS)의 중요성은 날로 커지고 있으며 네트워크의 보안을 보장하기 위한 방안으로서 널리 이용되고 있다. 그러나 작은 네트워크 환경에서도 IDsystem에 적용되는 audit data의 양이 많아짐으로서 시간당 처리속도와 IDsystem의 설정을 위한 시간이 더욱더 요구되며 전체적인 효율성이 감소하게 된다. 본 연구에서는 IDsystem으로 빠른 훈련과정과 일반화 능력, 구조적인 단순함으로 다양한 분야에서 연구가 진행 중인 신경망 모델 중 하나인 Radial Basis Function(RBF)를 사용하였으며, 효율성 제고를 위하여 RBF에 적용 할 입력 간들의 중요성을 선 처리 단계에서 판별하여 불필요한 입력 값들을 축약하기 위해 결정계수(R-square)같을 측정, 알려지지 않은 공격과 알려진 공격들을 판별 할 수 있는 IDsystem을 제안하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.470-473
• /
• 2021

외부인들이 시설을 무단으로 이용하는 등의 범죄가 계속해서 발생하고 있다. 본 논문은 기존의 시설물에서 사용하고 있는 단순 인증 절차가 아닌 BLE 비콘과 영상데이터를 활용한 비승인자 감지 시스템이다. 이 시스템은 스마트폰 어플리케이션에서 BLE 비콘의 데이터를 받은 후 UUID 값과 RSSI 값을 서버로 전송한다. 이후 전송된 데이터들로 핑거프린팅 기반 RadioMap을 구성하고 RNN 기반 딥러닝 학습을 진행하여 사용자 위치 데이터를 도출한다. CCTV를 통해 수집된 영상데이터는 서버로 전송되며, YOLOv4를 이용하여 객체탐지를 위한 프로세스를 진행한 후 Person 클래스를 추출한다. 이후 승인된 사용자의 위치 데이터에 실시간 영상데이터를 더하여 인증 과정 절차가 진행되지 않은 비승인자들을 추적한다. 본 논문은 COVID-19로 인해 시설물 인증 절차에 사용이 증가하고 있는 QR코드를 이용해 인증 과정 절차의 진행 방식으로 시스템에 대한 확장성까지 기대할 수 있다.

• Spatial Information Research
• /
• v.18 no.3
• /
• pp.23-32
• /
• 2010

LIDAR data are useful for forest applications such as bare-earth DEM generation for forest areas, and estimation of tree height and forest biomass. As a core preprocessing procedure for most forest applications, this study attempts to develop an efficient method to detect forest areas from LIDAR data. First, we suggest three perceptual cues based on multiple return characteristics, height deviation and spatial distribution, being expected as reliable perceptual cues for forest area detection from LIDAR data. We then classify the potential forest areas based on the individual cue and refine them with a bi-morphological process to eliminate falsely detected areas and smoothing the boundaries. The final refined forest areas have been compared with the reference data manually generated with an aerial image. All the methods based on three types of cues show the accuracy of more than 90%. Particularly, the method based on multiple returns is slightly better than other two cues in terms of the simplicity and accuracy. Also, it is shown that the combination of the individual results from each cue can enhance the classification accuracy.

• Journal of KIISE
• /
• v.41 no.12
• /
• pp.1066-1074
• /
• 2014

In this paper, we present a visual analytics system that uses serial-correlation to detect an abnormal event in spatio-temporal data. Our approach extracts the topic-model from spatio-temporal tweets and then filters the abnormal event candidates using a seasonal-trend decomposition procedure based on Loess smoothing (STL). We re-extract the topic from the candidates, and then, we apply STL to the second candidate. Finally, we analyze the serial-correlation between the first candidates and the second candidate in order to detect abnormal events. We have used a visual analytic approach to detect the abnormal events, and therefore, the users can intuitively analyze abnormal event trends and cyclical patterns. For the case study, we have verified our visual analytics system by analyzing information related to two different events: the 'Gyeongju Mauna Resort collapse' and the 'Jindo-ferry sinking'.

• Convergence Security Journal
• /
• v.19 no.5
• /
• pp.47-53
• /
• 2019

Network-based sharing of information has evolved into a cloud service environment today, increasing its number of users rapidly, but has become a major target for network-based illegal attackers.. In addition, IP spoofing among attackers' various attack techniques generally involves resource exhaustion attacks. Therefore, fast detection and response techniques are required. The existing detection method for IP spoofing attack performs the final authentication process according to the analysis and matching of traceback information of the client who attempted the connection request. However, the simple comparison method of traceback information may require excessive OTP due to frequent false positives in an environment requiring service transparency. In this paper, symmetric key cryptography based on traceback information is used as mutual authentication information to improve this problem. That is, after generating a traceback-based encryption key, mutual authentication is possible by performing a normal decryption process. In addition, this process could improve the overhead caused by false positives.

• The Journal of the Acoustical Society of Korea
• /
• v.17 no.8
• /
• pp.25-33
• /
• 1998

본 논문에서는 한 쌍의 센서를 이용하여 미지의 수중 음향 신호의 시간지연의 차 (Time Delay Difference)를 추정하고 탐지하는 알고리즘을 다루고 있다. 전형적인 시간지연 차의 최적화 추정 기법은 두 신호의 상관관계(Cross Correlation)에 의한 ML(Maximum likelihood)추정으로 구할 수 있지만, 실제 수중 음향 환경 하에서 시간 지연뿐만 아니라 표 적의 이동에 의하여 발생하는 도플러 효과로 신호의 주파수도 변하게 된다. 이러한 신호 주 파수의 올바른 고려 없이 단순히 두 신호의 시간지연만을 추정하는 방법은 불가피한 에러를 생성하게 된다. 본 논문에서는 시시각각 변하는 시간지연의 차를 구하기 위한 준 최적화 기 법인 확률분포 함수의 Recursive Filter에 시간 지연 차와 도플러효과의 2차원 확률분포 함 수를 적용한 추정 알고리즘을 제안한다. 관측된 신호의 리샘플링(Resampling)을 통하여 도 플러 효과를 보상한 후 2차원 Conditional likelihood를 구하고 Projection과 Correction 과정 을 통하여 시간지연과 도플러 효과에 대한 사후확률을 구한다. 그리고 이러한 알고리즘을 가상 시나리오에 대한 모의실험을 통하여 평가한다.