• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.211-213
• /
• 2017

최근 컴퓨터 네트워크를 활용하는 다양한 기기들이 개발되고 급격히 확산되면서, 컴퓨터 네크워크는 전보다 많은 보안문제에 직면하게 되었다. 이에 따라 네트워크 보안을 위한 침입탐지시스템의 필요성이 대두된다. 침입탐지시스템을 구현하기 위한 대표적인 데이터 셋으로는 KDD CUP 99(KDD'99)와 이후 KDD'99의 문제점을 보완하여 공개된 NSL-KDD가 있다. 본 논문에서는 KDD'99와 NSL-KDD를 소개하고 인공신경망을 통해 두 데이터 셋을 비교 분석하였다. Multi-Layer Perceptron을 사용해 데이터 셋을 분석해본 결과, KDD'99는 전체 정확도에서 더 높은 결과를 얻은 반면 공격 별 탐지 정확도 면에서는 NSL-KDD에 뒤쳐졌다.

• Journal of Environmental Health Sciences
• /
• v.19 no.4
• /
• pp.67-82
• /
• 1993

This study was performed to investigate the preventive effect of KDD against lead toxicity. KDD of 133, 266, 532 and 1,064 mg/kg were administered twice to the rats of Sprague-Dawley strain and then 300 mg/kg lead acetate was given to times, respectively. 1. The accumulation effects of KDD against to lead showed the changes of lead concentration by time variation. But, no statistical significance were showed on 8 and 10 weeks for kidney, spleen, 8 weeks for liver, and 4, 6 and 8 weeks for duodenum. In the femur, statistical significance existed during the whole experimental period. The relatively high concentration of lead detected in the feces of the experimental group means that KDD facilitated excretion of lead. 2. The histopathological effect of KDD against lead showed cytomegaly, karyomegaly, inclusion body, urinary cast and hemosiderin of kidney in the experimental group I (Pb 300 mg/kg). Recovery of KDD administrated group was inclined to increase by KDD concentration. But, spleen's histopathological recovery of KDD aginst to lead did not show as much as kidney. In conclusion, this study revealed the preventive effect of KDD against lead toxicity and its mechanism inferred to facilitate lead excretion in feces following hinderance of lead absorption in the gastric-intestine and organs.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1997.06a
• /
• pp.49-54
• /
• 1997

For the purpose of a flexible coded video transmission over a heterogeneous network, we propose a new packetization method for coded video data. The proposed method achieves small degradation of coded picture quality in case of packet discard at the network node and does not require heavy processing load for bitrate control operation. Computer simulation results show that the bitrate reduction from 384 kb/s to 192 kb/s does not cause severe degradation in picture quality.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.05a
• /
• pp.47-50
• /
• 2004

본 논문은 대량의 데이터를 처리하는 전염병에 관한 역학조사에 대한 과정을 KDD(Knowledge Discovery in Database)와 데이터마이닝 기법을 이용해서 의료 전문인들의 지식을 데이터베이스화하여 데이터 선정, 정제, 보강, 예측과 빠른 데이터 검출을 하도록 하였다. 그리고 각 바이러스의 동향은 데이터마이닝을 활용하므로 일부분만의 데이터를 산출하지 않고 전체적인 동향을 산출, 예측하도록 한다.

• 한국디지털정책학회:학술대회논문집
• /
• 2004.05a
• /
• pp.575-592
• /
• 2004

In modern dynamic management environment, there is growing recognition that? information & knowledge management systems are essential for CEO's efficient/effective decision making. As a key component to cope with this current, we suggest the management performance analysis syystem based on Knowledge Discovery in Database (KDD). The system measures management performance that is considered with both VA(Value- Added), which represents stakeholder's point of view and EVA(Economic Value-Added), which represents shareholder's point of view. The relation ship between management performance and some 80 financial ratios is analyzed, and then important financial ratios are drawn out. In analyzing the relationship, we applied KDD process which includes such as multidimensional cube, OLAP(On-Line Analytic Process), data mining and AHP(Analytic Hierarchy Process). To demonstrate the performance of the system, we conducted a case study using financial data over the 16-years from 1981 to 1996 of Korean automobile industry which is taken from database of KISF AS(Korea Investors Services Financial Analysis System).

• Journal of Multimedia Information System
• /
• v.6 no.4
• /
• pp.165-172
• /
• 2019

Machine-learning techniques have been actively employed to information security in recent years. Traditional rule-based security solutions are vulnerable to advanced attacks due to unpredictable behaviors and unknown vulnerabilities. By employing ML techniques, we are able to develop intrusion detection systems (IDS) based on anomaly detection instead of misuse detection. Moreover, threshold issues in anomaly detection can also be resolved through machine-learning. There are very few datasets for network intrusion detection compared to datasets for malicious code. KDD CUP 99 (KDD) is the most widely used dataset for the evaluation of IDS. Numerous studies on ML-based IDS have been using KDD or the upgraded versions of KDD. In this work, we develop an IDS model using CSE-CIC-IDS 2018, a dataset containing the most up-to-date common network attacks. We employ deep-learning techniques and develop a convolutional neural network (CNN) model for CSE-CIC-IDS 2018. We then evaluate its performance comparing with a recurrent neural network (RNN) model. Our experimental results show that the performance of our CNN model is higher than that of the RNN model when applied to CSE-CIC-IDS 2018 dataset. Furthermore, we suggest a way of improving the performance of our model.

• The Korean Journal of Applied Statistics
• /
• v.35 no.3
• /
• pp.335-346
• /
• 2022

Profile control chart aims to detect a change in the functional relationship of multivariate characteristics in the statistical process control. In monitoring two variables, a linear profile is of interest composed of the intercept and slope of one variable (response variable) against the other (explanatory variable). The previous studies on monitoring of the linear profile mostly assume that the explanatory variables are the same for all profiles. However, there are also cases where they vary depending on profiles. This paper intends to extend the monitoring method to where explanatory variables are different for each profile. We compare the new method's performance through simulation and apply it to monitoring a network intrusion using NSL-KDD data.

• Journal of the Society of Disaster Information
• /
• v.19 no.4
• /
• pp.924-935
• /
• 2023

Purpose: The central aim of this study is to leverage machine learning techniques for the classification of Intrusion Detection System (IDS) data, with a specific focus on identifying the variables responsible for enhancing overall performance. Method: First, we classified 'R2L(Remote to Local)' and 'U2R (User to Root)' attacks in the NSL-KDD dataset, which are difficult to detect due to class imbalance, using seven machine learning models, including Logistic Regression (LR) and K-Nearest Neighbor (KNN). Next, we use the SHapley Additive exPlanation (SHAP) for two classification models that showed high performance, Random Forest (RF) and Light Gradient-Boosting Machine (LGBM), to check the importance of variables that affect classification for each model. Result: In the case of RF, the 'service' variable and in the case of LGBM, the 'dst_host_srv_count' variable were confirmed to be the most important variables. These pivotal variables serve as key factors capable of enhancing performance in the context of classification for each respective model. Conclusion: In conclusion, this paper successfully identifies the optimal models, RF and LGBM, for classifying 'R2L' and 'U2R' attacks, while elucidating the crucial variables associated with each selected model.

• Journal of Digital Convergence
• /
• v.15 no.6
• /
• pp.391-398
• /
• 2017

In this paper, we compared the performance of "Network Intrusion Detection System based on attack feature selection using fuzzy control language"[1] and "Intelligent Intrusion Detection System Model for attack classification using RNN"[2]. In this paper, we compare the intrusion detection performance of two techniques using KDD CUP 99 dataset. The KDD 99 dataset contains data sets for training and test data sets that can detect existing intrusions through training. There are also data that can test whether training data and the types of intrusions that are not present in the test data can be detected. We compared two papers showing good intrusion detection performance in training and test data. In the comparative paper, there is a lack of performance to detect intrusions that exist but have no existing intrusion detection capability. Among the attack types, DoS, Probe, and R2L have high detection rate using fuzzy and U2L has a high detection rate using RNN.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.4
• /
• pp.795-805
• /
• 2019

Recently, there is a growing interest in network anomaly detection technology to tackle unknown attacks. For this purpose, diverse studies using data mining, machine learning, and deep learning have been applied to detect network anomalies. In this paper, we evaluate the decision tree to see its feasibility for network anomaly detection on NSL-KDD data set, which is one of the most popular data mining techniques for classification. In order to handle the over-fitting problem of decision tree, we select 13 features from the original 41 features of the data set using chi-square test, and then model the decision tree using TensorFlow and Scik-Learn, yielding 84% and 70% of binary classification accuracies on the KDDTest+ and KDDTest-21 of NSL-KDD test data set. This result shows 3% and 6% improvements compared to the previous 81% and 64% of binary classification accuracies by decision tree technologies, respectively.