• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.8
• /
• pp.4021-4037
• /
• 2018

In network intrusion detection research, two characteristics are generally considered vital to building efficient intrusion detection systems (IDSs): an optimal feature selection technique and robust classification schemes. However, the emergence of sophisticated network attacks and the advent of big data concepts in intrusion detection domains require two more significant aspects to be addressed: employing an appropriate big data computing framework and utilizing a contemporary dataset to deal with ongoing advancements. As such, we present a comprehensive approach to building an efficient IDS with the aim of strengthening academic anomaly detection research in real-world operational environments. The proposed system has the following four characteristics: (i) it performs optimal feature selection using information gain and branch-and-bound algorithms; (ii) it employs machine learning techniques for classification, namely, Logistic Regression, Naïve Bayes, and Random Forest; (iii) it introduces bulk synchronous parallel processing to handle the computational requirements of large-scale networks; and (iv) it utilizes a real-time contemporary dataset generated by the Information Security Centre of Excellence at the University of Brunswick (ISCX-UNB) to validate its efficacy. Experimental analysis shows the effectiveness of the proposed framework, which is able to achieve high accuracy, low computational cost, and reduced false alarms.

• Journal of KIISE:Information Networking
• /
• v.30 no.3
• /
• pp.397-406
• /
• 2003

As the information technology grows interests in the intrusion detection system (IDS), which detects unauthorized usage, misuse by a local user and modification of important data, has been raised. In the field of anomaly-based IDS several artificial intelligence techniques such as hidden Markov model (HMM), artificial neural network, statistical techniques and expert systems are used to model network rackets, system call audit data, etc. However, there are undetectable intrusion types for each measure and modeling method because each intrusion type makes anomalies at individual measure. To overcome this drawback of single-measure anomaly detector, this paper proposes a multiple-measure intrusion detection method. We measure normal behavior by systems calls, resource usage and file access events and build up profiles for normal behavior with hidden Markov model, statistical method and rule-base method, which are integrated with a rule-based approach. Experimental results with real data clearly demonstrate the effectiveness of the proposed method that has significantly low false-positive error rate against various types of intrusion.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.13 no.2
• /
• pp.99-106
• /
• 2003

Intrusions pose a serious security risk in a network environment. For detecting the intrusion effectively, many researches have developed data mining framework for constructing intrusion detection modules. Traditional anomaly detection techniques focus on detecting anomalies in new data after training on normal data. To detect anomalous behavior, Precise normal Pattern is necessary. This training data is typically expensive to produce. For this, the understanding of the characteristics of data on network is inevitable. In this paper, we propose to use clustering and association rules as the basis for guiding anomaly detection. For applying entropy to filter noisy data, we present a technique for detecting anomalies without training on normal data. We present dynamic transaction for generating more effectively detection patterns.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.13 no.4
• /
• pp.151-159
• /
• 2003

Internet as being generalized, intrusion detection system is needed to protect computer system from intrusions synthetically. We propose an intrusion detection method to identify and control the contradiction on self-explanation that happen at profiling process of anomaly detection methodology. Because many patterns can be created on profiling process with association method, we present effective application plan through clustering for rules. Finally, we propose similarity function to decide whether anomaly action or not for user pattern using clustered pattern database.

• 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.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.14 no.5
• /
• pp.69-78
• /
• 2004

The change of attack techniques paradigm was begun by fast extension of the latest Internet and new attack form appearing. But, Most intrusion detection systems detect only known attack type as IDS is doing based on misuse detection, and active correspondence is difficult in new attack. Therefore, to heighten detection rate for new attack pattern, the experiments to apply various techniques of anomaly detection are appearing. In this paper, we propose an behavior profiling method using Bayesian framework based on graphics from audit data and visualize behavior profile to detect/analyze anomaly behavior. We achieve simulation to translate host/network audit data into BF-XML which is behavior profile of semi-structured data type for anomaly detection and to visualize BF-XML as SVG.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.11
• /
• pp.449-456
• /
• 2021

An intrusion detection system is a technology that detects abnormal behaviors that violate security, and detects abnormal operations and prevents system attacks. Existing intrusion detection systems have been designed using statistical analysis or anomaly detection techniques for traffic patterns, but modern systems generate a variety of traffic different from existing systems due to rapidly growing technologies, so the existing methods have limitations. In order to overcome this limitation, study on intrusion detection methods applying various machine learning techniques is being actively conducted. In this study, a comparative study was conducted on data preprocessing techniques that can improve the accuracy of anomaly detection using NGIDS-DS (Next Generation IDS Database) generated by simulation equipment for traffic in various network environments. Padding and sliding window were used as data preprocessing, and an oversampling technique with Adversarial Auto-Encoder (AAE) was applied to solve the problem of imbalance between the normal data rate and the abnormal data rate. In addition, the performance improvement of detection accuracy was confirmed by using Skip-gram among the Word2Vec techniques that can extract feature vectors of preprocessed sequence data. PCA-SVM and GRU were used as models for comparative experiments, and the experimental results showed better performance when sliding window, skip-gram, AAE, and GRU were applied.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.6 s.38
• /
• pp.9-16
• /
• 2005

Recently, since the number of internet users is increasing rapidly and, by using the Public hacking tools, general network users can intrude computer systems easily, the hacking problem is setting more serious. In order to prevent the intrusion. it is needed to detect the sign in advance of intrusion in a Positive Prevention by detecting the various forms of hackers intrusion trials to know the vulnerability of systems. The existing network-based anomaly detection algorithms that cope with port-scanning and the network vulnerability scans have some weakness in intrusion detection. they can not detect slow scans and coordinated scans. therefore, the new concept of algorithm is needed to detect effectively the various. In this Paper, we propose a detection algorithm for session patterns and FCM.

• Journal of Internet Computing and Services
• /
• v.4 no.2
• /
• pp.69-80
• /
• 2003

Program Behavior Intrusion Detection Technique analyses system calls that called by daemon program or root authority, constructs profiles, and detectes modificated anomaly intrusions effectively. In this paper, the relation among system calls of processes is represented by bayesian network and Multiple Sequence Alignment. Program behavior profiling by Bayesian Network classifies modified anomaly intrusion behaviors, and detects anomaly behaviors. we had simulation by proposed normal behavior profiling technique using UNM data.

• The KIPS Transactions:PartC
• /
• v.10C no.5
• /
• pp.525-532
• /
• 2003

This paper describes intrusion detection rule management using mobile agents. Intrusion detection can be divided into anomaly detection and misuse detection. Misuse detection is best suited for reliably detecting known use patterns. Misuse detection systems can detect many or all known attack patterns, but they are of little use for as yet unknown attack methods. Therefore, the introduction of mobile agents to provide computational security by constantly moving around the Internet and propagating rules is presented as a solution to misuse detection. This work presents a new approach for detecting intrusions, in which mobile agent mechanisms are used for security rules propagation. To evaluate the proposed approach, we compared the workload data between a rules propagation method using a mobile agent and a conventional method. Also, we simulated a rules management using NS-2 (Network Simulator) with respect to time.