• The Journal of the Korea institute of electronic communication sciences
• /
• v.9 no.6
• /
• pp.695-701
• /
• 2014

Blackhole attacks having a unauthorized change of routing data will cause critical effects for transmission performance. The transmission performance will be improved to the a certain level by using or having IDS(Intrusion Detection System)/IPS(Intrusion Prevention System) as countermeasures to blackhole attacks. In this papar, the effects of IDS to ene-to-end performance of packet aggregation transmission are analyzed on MANET(Mobile Ad-hoc Network) with IDS under blackhole attacks. MANET simulator based on NS-2 is used to analyze performance parameters as MOS, connection ratio, delay and packet loss rate as standard performance parameters, an another performance factor which is suggested in this paper. VoIP(Voice over Internet Protocol) traffics, one of voice services, is used for performance analysis. A suggestion for IDS implementation on MANET with packet aggregations under blackhole is shown as one of results.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.05d
• /
• pp.951-954
• /
• 2002

최근의 침입탐지시스템(IDS: Intrusion Detection System) 기술동향은 Misuse 방식의 규칙 데이터베이스 변경에 대한 한계성 때문에 Anomaly 방식의 NIDS(Network IDS)에 대한 연구가 고려되고 있다. 현재 국내에서 개발된 기존의 제품들은 대부분 Misuse 방식을 채택하고 있으며, 향후 국제 경쟁력을 갖추기 위해서는 Anomaly 방식의 기술 연구가 필요하다. 본 연구에서는 본 연구실에서 개발한 NIDS를 기반으로 연관 마이닝을 이용한 비정상 탐지 문제, 내부 정보 유출 차단 등에 대한 통합된 시스템 설계 방향을 제시하여 국가기관이나 기업이 보다 안전하게 침입을 관리할 수 있는 IPS(Intrusion Prevention System) 시스템을 설계한다.

• Journal of information and communication convergence engineering
• /
• v.2 no.2
• /
• pp.84-88
• /
• 2004

Firewall is not perfectly prevent hacker, Intrusion Detection System(IDS) is considered a next generation security solution for more trusted network i and system security. We propose a agent IDS model in the different platforms that can detect intrusions in the expanded distributed host environment, since that is a drawback of existing IDS. Then we implement a prototype and verify validity. We use a pattern extraction agent so that we extract audit files needed in intrusion detection automatically even in other platforms.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.11 no.4
• /
• pp.33-45
• /
• 2015

Currently, Internet is used an essential tool in the business area. Despite this importance, there is a risk of network attacks attempting collection of fraudulence, private information, and cyber terrorism. Firewalls and IDS(Intrusion Detection System) are tools against those attacks. IDS is used to determine whether a network data is a network attack. IDS analyzes the network data using various techniques including expert system, data mining, and state transition analysis. This paper tries to compare the performance of two data mining models in detecting network attacks. They are decision tree (C4.5), and neural network (FANN model). I trained and tested these models with data and measured the effectiveness in terms of detection accuracy, detection rate, and false alarm rate. This paper tries to find out which model is effective in intrusion detection. In the analysis, I used KDD Cup 99 data which is a benchmark data in intrusion detection research. I used an open source Weka software for C4.5 model, and C++ code available for FANN model.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.05c
• /
• pp.2213-2216
• /
• 2003

단일 호스트 환경에 특화되어 설계되어온 기존 침입탐지 시스템(Intrusion Detection System: IDS)은 침입 시 도메인의 보호만을 그 목적으로 하는 수동적인 성격으로써, 새로운 공격 기법에 대한 탐지 및 대응, 그리고 보다 그 규모가 큰 네트워크로의 확장 면에서 구조적인 결함을 가지고 있다. 이러한 IDS의 구조적 문제점의 해결방안으로 액티브 네트워크 기반의 IDS 에 관한 연구가 진행되고 있다. 액티브 네트워크(Active network)란 패킷 스위칭 네트워크 상에 프로그램 가능한 라우터 등인 액티브 노드들을 배치하고, 사용자의 요구에 상응하는 적절한 연산을 위한 데이터와 프로그램으로 구성된 스마트 패킷(smart packet)에 대하여 수행 가능하게 하는 접근 방법이다. 본 논문에서는 이를 기반으로 자율적이며 지능적인 에이전트로 구성된 멀티 에이전트 기술을 액티브 노드에 적용함으로써 기존 IDS 보안메커니즘에서 보다 러 진보된 능동적이고 적극적인 대응을 위한 보안 메커니즘을 제공하여 네트워크 공격에 의한 피해 최소화와 신속한 대응이 가능한 멀티 에이전트 기반 공격 대응 메커니즘을 제시하고, 이를 적용 가능한 액티브 네트워크 기반 프레임 설계를 제안한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.11b
• /
• pp.893-896
• /
• 2002

네트워크 발달로 컴퓨터 시스템에 대한 접근이 용이해 지면서 호기심 또는 악의로 시스템을 침입 및 파괴하려는 다양한 형태의 침입 행위가 날로 증가하고 있다. 이러한 침입에 대비하여 대상 시스템에 대한 비 인가된 행위를 탐지 및 구별하고 이에 대응하는 기능을 가진 침입 탐지 시스템(IDS: Intrusion Detection System)에 대한 연구가 폭 넓게 진행되어 왔으며 다양한 형태의 IDS 들이 컴퓨터 및 네트워크 시스템에 적용되고 있다. 그러나 일반적인 IDS 는 단일 시스템에 대한 침입을 탐지하고 방어하는 것에 그 목적이 있으므로, 하나의 단위 네트워크 시스템을 효과적으로 보호하기 위해서는 단일 시스템에 대한 침입정보를 신속하게 상호 공유할 필요가 있다. 따라서 개별 Host 나 Network 장비에 분산되어 동작하는 다중의 IDS 에 대해서 통합 관리를 수행하는 통합 침입 관리시스템이 요구되어진다. 본 논문에서 제안하는 시스템은 각 IDS 들이 침입을 탐지하는 순간 이에 대한 정보를 수집하여 다른 IDS 들에게 침입에 대한 정보를 신속하게 전달하고, 정보의 종류와 수행 기능에 따른 요구사항을 프로토콜에 적절하게 반영 할 수 있는 시스템을 제안한다.

• Journal of Multimedia Information System
• /
• v.3 no.3
• /
• pp.91-96
• /
• 2016

Network security is an interesting area in Information Technology. It has an important role for the manager monitor and control operating of the network. There are many techniques to help us prevent anomaly or malicious activities such as firewall configuration etc. Intrusion Detection System (IDS) is one of effective method help us reduce the cost to build. The more attacks occur, the more necessary intrusion detection needs. IDS is a software or hardware systems, even though is a combination of them. Its major role is detecting malicious activity. In recently, there are many researchers proposed techniques or algorithms to build a tool in this field. In this paper, we improve the performance of IDS. We explore and analyze the impact of activation functions applying to recurrent neural network model. We use to KDD cup dataset for our experiment. By our experimental results, we verify that our new tool of IDS is really significant in this field.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.7
• /
• pp.3714-3732
• /
• 2019

With the rapid development of network, Intrusion Detection System(IDS) plays a more and more important role in network applications. Many data mining algorithms are used to build IDS. However, due to the advent of big data era, massive data are generated. When dealing with large-scale data sets, most data mining algorithms suffer from a high computational burden which makes IDS much less efficient. To build an efficient IDS over big data, we propose a classification algorithm based on data clustering and data reduction. In the training stage, the training data are divided into clusters with similar size by Mini Batch K-Means algorithm, meanwhile, the center of each cluster is used as its index. Then, we select representative instances for each cluster to perform the task of data reduction and use the clusters that consist of representative instances to build a K-Nearest Neighbor(KNN) detection model. In the detection stage, we sort clusters according to the distances between the test sample and cluster indexes, and obtain k nearest clusters where we find k nearest neighbors. Experimental results show that searching neighbors by cluster indexes reduces the computational complexity significantly, and classification with reduced data of representative instances not only improves the efficiency, but also maintains high accuracy.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.12
• /
• pp.3622-3633
• /
• 1999

Computer security is considered important due to tile side effect generated from the expansion of computer network and rapid increase of the use of computers. Intrusion Detection System(IDS) has been an active research area to reduce the risk from intruders. This paper discusses IDS of detecting anomaly behaviors and proposes a new intelligent IDS model, which consists of several computers with intelligent IDS, based on computer immune system. The intelligent IDSs are distributed and if any of distributed IDSs detect anomaly system call among system call sequences generated by a privilege process, the anomaly system call can be dynamically shared with other IDSs. This makes the intelligent IDSs improve the ability of immunity for new intruders.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2008.10a
• /
• pp.525-528
• /
• 2008

We propose a IDS node selection scheme for intrusion detection in wireless mesh networks. The proposed scheme considers network survivability and energy consumption. To utilize wireless resources efficiently, we apply a set covering problem (SCP) to IDS nodes selection problem. Our proposed scheme also considers congested networks.