• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.355-364
• /
• 2023

As advanced cyber threats continue to increase in recent years, it is difficult to detect new types of cyber attacks with existing pattern or signature-based intrusion detection method. Therefore, research on anomaly detection methods using data learning-based artificial intelligence technology is increasing. In addition, supervised learning-based anomaly detection methods are difficult to use in real environments because they require sufficient labeled data for learning. Research on an unsupervised learning-based method that learns from normal data and detects an anomaly by finding a pattern in the data itself has been actively conducted. Therefore, this study aims to extract a latent vector that preserves useful sequence information from sequence log data and develop an anomaly detection learning model using the extracted latent vector. Word2Vec was used to create a dense vector representation corresponding to the characteristics of each sequence, and an unsupervised autoencoder was developed to extract latent vectors from sequence data expressed as dense vectors. The developed autoencoder model is a recurrent neural network GRU (Gated Recurrent Unit) based denoising autoencoder suitable for sequence data, a one-dimensional convolutional neural network-based autoencoder to solve the limited short-term memory problem that GRU can have, and an autoencoder combining GRU and one-dimensional convolution was used. The data used in the experiment is time-series-based NGIDS (Next Generation IDS Dataset) data, and as a result of the experiment, an autoencoder that combines GRU and one-dimensional convolution is better than a model using a GRU-based autoencoder or a one-dimensional convolution-based autoencoder. It was efficient in terms of learning time for extracting useful latent patterns from training data, and showed stable performance with smaller fluctuations in anomaly detection performance.

• Journal of Software Assessment and Valuation
• /
• v.15 no.2
• /
• pp.43-50
• /
• 2019

With the development of IT technology, computer-related crimes are rapidly increasing, and in recent years, the damage to ransomware infections is increasing rapidly at home and abroad. Conventional security solutions are not sufficient to prevent ransomware infections, and to prevent threats such as malware and ransomware that are evolving, a combination of deep learning technologies is needed to detect abnormal behavior and abnormal symptoms. In this paper, a method is proposed to detect user abnormal behavior using CNN-LSTM model and various deep learning models. Among the proposed models, CNN-LSTM model detects user abnormal behavior with 99% accuracy.

• Journal of Internet Computing and Services
• /
• v.23 no.6
• /
• pp.39-48
• /
• 2022

Cyberattacks around the world continue to increase, and their damage extends beyond government facilities and affects civilians. These issues emphasized the importance of developing a system that can identify and detect cyber anomalies early. As above, in order to effectively identify cyber anomalies, several studies have been conducted to learn BGP (Border Gateway Protocol) data through a machine learning model and identify them as anomalies. However, BGP data is unbalanced data in which abnormal data is less than normal data. This causes the model to have a learning biased result, reducing the reliability of the result. In addition, there is a limit in that security personnel cannot recognize the cyber situation as a typical result of machine learning in an actual cyber situation. Therefore, in this paper, we investigate BGP (Border Gateway Protocol) that keeps network records around the world and solve the problem of unbalanced data by using SMOTE. After that, assuming a cyber range situation, an autoencoder classifies cyber anomalies and visualizes the classified data. By learning the pattern of normal data, the performance of classifying abnormal data with 92.4% accuracy was derived, and the auxiliary index also showed 90% performance, ensuring reliability of the results. In addition, it is expected to be able to effectively defend against cyber attacks because it is possible to effectively recognize the situation by visualizing the congested cyber space.

• Smart Media Journal
• /
• v.13 no.4
• /
• pp.48-56
• /
• 2024

In the livestock industry, detecting environmental outliers and predicting data are crucial tasks. Outliers in livestock environment data, typically gathered through time-series methods, can signal rapid changes in the environment and potential unexpected epidemics. Prompt detection and response to these outliers are essential to minimize stress in livestock and reduce economic losses for farmers by early detection of epidemic conditions. This study employs two methods to experiment and compare performances in setting thresholds that define outliers in livestock environment data outlier detection. The first method is an outlier detection using Mean Squared Error (MSE), and the second is an outlier detection using a Dynamic Threshold, which analyzes variability against the average value of previous data to identify outliers. The MSE-based method demonstrated a 94.98% accuracy rate, while the Dynamic Threshold method, which uses standard deviation, showed superior performance with 99.66% accuracy.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.209-212
• /
• 2021

현재 IT 보안 관제 시스템을 구축하여 사용하고 있는 기업들은 여러 보안 솔루션을 도입하고 있어 각 솔루션에 따라 서로 다른 IT 이상징후 탐지 모델을 필요로 하고 있다. 이에 따라 솔루션별로 상이한 모델이 필요하며, 유지보수에 어려움이 대두되었다. 이러한 보안 관제 시장의 문제를 해결하기 위해 요구된 것이 이기종 보안 솔루션의 공통 정보 모델로의 표준화 및 탐지 모델 체계화이다. 현재 JCIM은 보안 관제 시장에서 데이터를 공통 정보 모델로 표준화하고, 선택한 솔루션의 시나리오를 보여주며 즉시 탐지까지 가능한 제품을 구현하였다. 이를 통해 AI 기반의 이상 탐지 시나리오를 구현할 수 있는 인력을 양성하고, 이를 기반으로 다양한 고객(산업군)사에 적응하는 것을 기대한다.

• The Journal of Society for e-Business Studies
• /
• v.19 no.4
• /
• pp.119-134
• /
• 2014

Financial companies are providing electronic financial transactions through a variety of user terminals for non-face-to-face services such as Internet banking, smart phone banking, or etc. However, in these services users' security awareness and the limitations of technical responses has frequently caused the financial loss so that fundamental protection measures are required from financial authorities. Accordingly, financial industry is planning and establishing systems that block unusual financial transactions by comprehensively analyzing and detecting user's electronic information, access information, transaction information, and so on in accordance with "Guide for building Unusual financial transactions detection system" to prevent the financial loss that happens in electronic financial transactions. In this paper, we analyze case studies of unusual financial transactions detection and prevention system that is built and operated in financial companies and current operating status and propose effects of the accident prevention and security measures later.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.25 no.3
• /
• pp.615-625
• /
• 2015

This paper proposes new methods and examples for improving fraud detection rules based on banking customer's transaction behaviors focused on anomaly detection method. This study investigates real example that FDS(Fraud Detection System) regards fraudulent transaction as legitimate transaction and figures out fraudulent types and transaction patterns. To understanding the cases that FDS regard legitimate transaction as fraudulent transaction, it investigates all transactions that requied additional authentications or outbound call. We infered additional facts to refine detection rules in progress of outbound calling and applied to existing detection rules to improve. The main results of this study is the following: (a) Type I error is decreased (b) Type II errors are also decreased. The major contribution of this paper is the improvement of effectiveness in detecting fraudulent transaction using transaction behaviors and providing a continuous method that elevate fraud detection rules.

• Convergence Security Journal
• /
• v.12 no.4
• /
• pp.77-84
• /
• 2012

The control network has been operated in a closed. But it changes to open to external for business convenience and cooperation with several organizations. As the way of connecting with user extends, the risk of control network gets high. Thus, in this paper, proposed the technique of an anomalous event detection using white-list for control network security and minimizing the cyber threats. The proposed method can be collected and cataloged of only normal data from traffic of internal network, control network and field devices. Through way to check the this situation, we can separate normal and abnormal behavior.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.57-60
• /
• 2021

본 논문에서는 기지 설비 중 주요 회전기기인 펌프의 이상탐지 알고리즘을 제안한다. 현재 인공지능을 활용하여 생산현장을 혁신하고자 하는 시도가 진행되고 있으나 외산 솔루션에 대한 의존도가 높은 것에 비해 국내 실정에 맞지 않는 경우가 많다. 이에 따라, 선행 연구를 통해 국내 실정에 맞는 인공지능 기술 도입이 필요하다. 본 연구에서는 VAE(Variational Auto Encoder) 알고리즘을 활용해 회전기기의 고장을 진단하는 알고리즘을 개발하였다. 본 연구 수행을 통한 회전기기의 고장 예지·진단 시스템 개발로 설비의 이상 징후 포착, 부품의 교환 시기 등 보수 일정을 예측하고 최종적으로 이를 통한 설비 가동의 효율 증대와 에너지 비용 감소의 효과를 기대한다.

• Proceedings of the Korea Contents Association Conference
• /
• 2019.05a
• /
• pp.329-330
• /
• 2019

인터넷 기술 및 통신 기술의 급격한 발전과 사물 인터넷을 기반으로 산업 구조가 재편됨에 따라 점차 지능화, 다변화 있는 보안 위협들에 대하여 기존 시스템 보안 중심의 취약성 분석 및 데이터 암호화를 통해 구성된 보안 시스템은 한계를 보이고 있다. 특히 외부 침입 방지를 위해 별도의 사설망을 구축하여 물리적으로 분리된 보안망에 대한 악성코드 유입 등의 보안 위협 발생도 꾸준히 증가하고 있으며 보안 침해 상황 발생 시 빠른 대응도 점차 어려워지고 있다. 이에 본 연구에서는 새로운 유형의 보안 취약성 탐지를 위해 기존 보안 시스템을 구성하는 리엑티브(reactive) 기법 및 휴리스틱(heuristic) 탐지 기법이 아닌 네트워크 패킷 수집 및 분석과 대상 시스템의 비지니스 모델 매칭을 통한 사용자 행위 패턴을 해석하였다. 그리고 실시간 행위 분석을 수행하여 사용자 행위 중심의 이상 징후 감시 기준을 설립함으로써 보안 위협에 대한 행위 유형 판단 기준 및 이상 감지 판단 방법에 대해 제안한다.