• 정보보호학회논문지
• /
• 제14권5호
• /
• pp.69-78
• /
• 2004

인터넷의 급속한 확장과 새로운 공격 형태의 출현으로 인해 공격 기법 패러다임의 변화가 시작되었다. 그러나, 대부분의 침입 탐지 시스템은 오용 탐지 기반의 알려진 공격 유형만을 탐지하며, 새로운 공격에 대해서는 능동적인 대응이 어려운 실정이다. 이에 새로운 공격 유형에 대한 탐지 능력을 높이기 위해 이상 탐지의 여러 기법들을 적용하려는 시도들이 나타나고 있다. 본 논문에서는 그래픽 기반의 베이지안 프레임워크를 이용하여 감사 데이터에 의한 행위 프로파일링 방법을 제안하고 이상 탐지와 분석을 위한 행위 프로파일을 시각화하고자 한다. 호스트/네트워크의 감사 데이터를 이상 탐지를 위한 준 구조적 데이터 형식의 행위 프로파일인 BF-XML로 변환하고, BF-XML을 SVG로 시각화를 시뮬레이션한다.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.77-91
• /
• 2022

Various monitoring systems have been implemented in civil infrastructure to ensure structural safety and integrity. In long-term monitoring, these systems generate a large amount of data, where anomalies are not unusual and can pose unique challenges for structural health monitoring applications, such as system identification and damage detection. Therefore, developing efficient techniques is quite essential to recognize the anomalies in monitoring data. In this study, several machine learning techniques are explored and implemented to detect and classify various types of data anomalies. A field dataset, which consists of one month long acceleration data obtained from a long-span cable-stayed bridge in China, is employed to examine the machine learning techniques for automated data anomaly detection. These techniques include the statistic-based pattern recognition network, spectrogram-based convolutional neural network, image-based time history convolutional neural network, image-based time-frequency hybrid convolution neural network (GoogLeNet), and proposed ensemble neural network model. The ensemble model deliberately combines different machine learning models to enhance anomaly classification performance. The results show that all these techniques can successfully detect and classify six types of data anomalies (i.e., missing, minor, outlier, square, trend, drift). Moreover, both image-based time history convolutional neural network and GoogLeNet are further investigated for the capability of autonomous online anomaly classification and found to effectively classify anomalies with decent performance. As seen in comparison with accuracy, the proposed ensemble neural network model outperforms the other three machine learning techniques. This study also evaluates the proposed ensemble neural network model to a blind test dataset. As found in the results, this ensemble model is effective for data anomaly detection and applicable for the signal characteristics changing over time.

• ETRI Journal
• /
• 제34권2호
• /
• pp.288-291
• /
• 2012

In this letter, a new online anomaly detection approach for software systems is proposed. The novelty of the proposed approach is to apply a new semantic kernel function for a support vector machine (SVM) classifier to detect fault-suspicious execution paths at runtime in a reasonable amount of time. The kernel uses a new sequence matching algorithm to measure similarities among program execution paths in a customized feature space whose dimensions represent the largest common subpaths among the execution paths. To increase the precision of the SVM classifier, each common subpath is given weights according to its ability to discern executions as correct or anomalous. Experiment results show that compared with the known kernels, the proposed SVM kernel will improve the time overhead of online anomaly detection by up to 170%, while improving the precision of anomaly alerts by up to 140%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권9호
• /
• pp.4684-4705
• /
• 2019

Collaborative filtering recommender systems are vulnerable to shilling attacks in which malicious users may inject biased profiles to promote or demote a particular item being recommended. To tackle this problem, many robust collaborative recommendation methods have been presented. Unfortunately, the robustness of most methods is improved at the expense of prediction accuracy. In this paper, we construct a robust Bayesian probabilistic matrix factorization model for collaborative filtering recommender systems by incorporating the detection of user anomaly rating behaviors. We first detect the anomaly rating behaviors of users by the modified K-means algorithm and target item identification method to generate an indicator matrix of attack users. Then we incorporate the indicator matrix of attack users to construct a robust Bayesian probabilistic matrix factorization model and based on which a robust collaborative recommendation algorithm is devised. The experimental results on the MovieLens and Netflix datasets show that our model can significantly improve the robustness and recommendation accuracy compared with three baseline methods.

• International Journal of Contents
• /
• 제18권2호
• /
• pp.68-80
• /
• 2022

The health of the human heart is commonly measured using ECG (Electrocardiography) signals. To identify any anomaly in the human heart, the time-sequence of ECG signals is examined manually by a cardiologist or cardiac electrophysiologist. Lightweight anomaly detection on ECG signals in an embedded system is expected to be popular in the near future, because of the increasing number of heart disease symptoms. Some previous research uses deep learning networks such as LSTM and BiLSTM to detect anomaly signals without any handcrafted feature. Unfortunately, lightweight LSTMs show low precision and heavy LSTMs require heavy computing powers and volumes of labeled dataset for symptom classification. This paper proposes an ECG anomaly detection system based on two level BiLSTM for acceptable precision with lightweight networks, which is lightweight and usable at home. Also, this paper presents a new threshold technique which considers statistics of the current ECG pattern. This paper's proposed model with BiLSTM detects ECG signal anomaly in 0.467 ~ 1.0 F₁ score, compared to 0.426 ~ 0.978 F₁ score of the similar model with LSTM except one highly noisy dataset.

• 한국산업정보학회논문지
• /
• 제14권3호
• /
• pp.22-29
• /
• 2009

컴퓨터를 통해서 들어오는 다양한 형태의 침입을 효과적으로 탐지하기 위해서 이전에는 오용탐지 기법이 주로 이용되어 왔다. 오용탐지 기법은 이전에 알려지지 않은 침입 방법들을 효과적으로 탐지할 수 있기 때문이다. 하지만, 해당 기법에서는 정상적인 네트워크 접속 형태가 몇 가지 패턴으로 고정되어 있다고 가정한다. 이러한 이유 때문에 새로운 정상적인 네트워크 연결이 비정상행위로 탐지되기도 한다. 본 논문에서는 연관 마이닝 기법을 활용한 침입 탐지 방법을 제안한다. 논문에서 제안되는 방법은 패킷내 마이닝 단계와 패킷간 마이닝 두가지 단계로 구성된다. 제안된 방법의 성능은 대표적인 네트워크 침입 탐지 방법인 JAM과의 비교 실험을 통하여 평가하였다.

• 전자공학회논문지CI
• /
• 제38권5호
• /
• pp.37-43
• /
• 2001

인터넷이 널리 이용되면서 네트워크나 호스트에 대한 불법적인 침입은 많은 위험요소가 되고 있다. 이러한 침입을 탐지하기 위하여 통계적기법, 데이터마이닝기법, 유전자 알고리즘/프로그래밍 기법 등을 이용한 이상현상 탐지모델들이 많이 제안되어 왔으나 새로운 유형의 침입에 대해서는 탐지능력이 떨어지는 단점이 있다. 본 논문에서는 THRE KBANN을 이용한 이상현상탐지모델을 제안하였는데, 이는 연속학습을 할 수 있도록 지식기반신경망을 개선한 것이다. 이 모델을 실험적 자료에 적용한 결과를 데이터마이닝기법을 적용한 경우와 비교하여 성능평가를 하였다. 그리고 새로운 침입유형을 탐지하기 위한 연속학습에 대한 성능도 평가하였다.

• 정보보호학회논문지
• /
• 제32권1호
• /
• pp.39-48
• /
• 2022

본 논문에서는 무인 비행체 내부 네트워크의 이상 징후를 탐지하는 시퀀스 기반 이상 탐지 시스템을 제안한다. 제안하는 이상 탐지 시스템은 무인 비행체가 지상 통제 시스템에 주기적으로 전송하는 상태 메시지 시퀀스들 간의 유사도를 측정하여 이상 징후를 탐지한다. 본 연구에서는 무인 비행체 내부 네트워크에서 수행 가능한 악의적인 메시지 주입 공격 세 가지를 정의하고, 해당 공격 기법들을 Pixhawk4 쿼드콥터에서 시뮬레이션하였다. 결과적으로, 제안하는 이상 탐지 시스템은 96% 이상의 정확도로 비정상 시퀀스를 탐지할 수 있었다.

• 산업경영시스템학회지
• /
• 제46권2호
• /
• pp.1-12
• /
• 2023

To make semiconductor chips, a number of complex semiconductor manufacturing processes are required. Semiconductor chips that have undergone complex processes are subjected to EDS(Electrical Die Sorting) tests to check product quality, and a wafer bin map reflecting the information about the normal and defective chips is created. Defective chips found in the wafer bin map form various patterns, which are called defective patterns, and the defective patterns are a very important clue in determining the cause of defects in the process and design of semiconductors. Therefore, it is desired to automatically and quickly detect defective patterns in the field, and various methods have been proposed to detect defective patterns. Existing methods have considered simple, complex, and new defect patterns, but they had the disadvantage of being unable to provide field engineers the evidence of classification results through deep learning. It is necessary to supplement this and provide detailed information on the size, location, and patterns of the defects. In this paper, we propose an anomaly detection framework that can be explained through FCDD(Fully Convolutional Data Description) trained only with normal data to provide field engineers with details such as detection results of abnormal defect patterns, defect size, and location of defect patterns on wafer bin map. The results are analyzed using open dataset, providing prominent results of the proposed anomaly detection framework.

• 한국수소및신에너지학회논문집
• /
• 제33권1호
• /
• pp.85-94
• /
• 2022

To detect anomaly signs of thermal runaway in advance, this study analyzed the signals from various sensors installed in lithium-ion batteries. The thermal runaway mechanism was analyzed, and measurement variables for anomalies of a battery cell were surface temperature, strain, and gas concentration. The changes and characteristics of three variables during the thermal runaway process were analyzed under the abuse environment: the overheat and the overcharge. In experiment, the thermal runaway of the battery proceeded in the initial developing stage, the outgassing stage, and the ignition stage. Analysis from the measured data indicated that the suitable variable to detect all stages of thermal runaway is the surface temperature of the battery, and surface strain is alternative.