• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10a
• /
• pp.664-666
• /
• 2001

침입탐지의 종류를 탐지 방법 측면에서 구분해보면 크게 이상탐지와 오용탐지로 나뉘어진다. 침입탐지의 주된 목적은 탐지오류를 줄이고 정확한 침입을 판가름하는데 있다. 그러나 기존의 이상탐지와 오용탐지 기법은 그 방법론상에 이미 판단오류 가능성을 내포하고 있다. 이상탐지는 정상적인 사용에 대한 템플릿을 기초로 하므로 불규칙적인 사용에 대처할 수 없고, 오용탐지는 침입 시나리오라는 템플릿에 기초하므로 알려지지 않은 침입에 무방비 상태인 문제가 있다. 침입의 주요 목적은 관리자의 권한을 얻는 것이며 그 상태에서 쉘을 얻은 후 원하는 바를 행하는 데 있을 것이다. 그러므로 그 상태를 얻으려는 프로세스와 추이와 결과를 모니터링하여 대처하면 호스트기반 침입의 근본적인 해결책이 될 수 있다. 그러므로 본 연구에서는 프로세스의 상태를 모니터링함으로써 컴퓨터시스템의 침입을 탐지하는 새로운 기술에 대해 제안하고 설명한다. 프로세스의 상태는 일반상태, 특권상태 관리자상태 등으로 구분되며, 시스템에 의해 부여된 실사용자ID, 유효ID, 실그룹ID, 유효그룹ID를 점검함으로써 이루어진다. 본 연구에서 모니터링에는 BSM을 사용하며, 호스트기반에서 사용한 프로세스의 상태 모니터링에 의한 침입탐지시스템 구현한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10c
• /
• pp.318-320
• /
• 1999

정보시스템의 보호를 위한 침입탐지의 방법으로 오용탐지와 비정상행위 탐지방법이 있다. 오용탐지의 경우는 알려진 침입 패턴을 이용하는 것으로 알려진 침입에 대해서는 아주 높은 탐지율을 나타내지만 알려지지 않은 침입이나 변형패턴에 대해서는 탐지할 수 없다는 단점이 있다. 반면 비정상행위 탐지는 정상행위 모델링을 통해 비정상패턴을 탐지하는 것으로 알려지지 않은 패턴에 대해서도 탐지할 수 있는 장점이 있는데 국내외적으로 아직까지 널리 연구되어 있지 않다. 본 논문에서는 BSM으로부터 얻은 다양한 정보를 추출하고 이러한 정보를 자기조직화 신경망을 이용하여 축약함으로써 고정된 크기의 순서정보로 변환하는 방법을 제안한다. 이렇게 생성된 고정크기의 순서정보는 비정상행위 탐지에 효과적으로 사용될 수 있을 것이다.

• Proceedings of the Korea Institutes of Information Security and Cryptology Conference
• /
• 2003.12a
• /
• pp.179-184
• /
• 2003

컴퓨터를 통한 침입을 탐지하기 위해서 많은 연구들이 오용탐지 기법을 개발하였다. 최근에는 오용 탐지 기법을 개선하기 위해서 비정상행위 탐지 기법에 관련된 연구들이 진행중이다. 본 논문에서는 클러스터링 기법을 응용한 새로운 네트워크 비정상행위 탐지 기법을 제안한다. 이를 위해서 정상 행위를 다양한 각도에서 분석될 수 있도록 네트워크 로그로부터 여러 특징들을 추출하고 각 특징에 대해서 클러스터링 알고리즘을 이용하여 정상행위 패턴을 생성한다. 제안된 방법에서는 정상행위 패턴 즉 클러스터를 축약된 프로파일로 생성하는 방법을 제시하며 제안된 방법의 성능을 평가하기 위해서 DARPA에서 수집된 네트워크 로그를 이용하였다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.14 no.3
• /
• pp.22-29
• /
• 2009

In previous work, anomaly-based intrusion detection techniques have been widely used to effectively detect various intrusions into a computer. This is because the anomaly-based detection techniques can effectively handle previously unknown intrusion methods. However, most of the previous work assumed that the normal network connections are fixed. For this reason, a new network connection may be regarded as an anomalous event. This paper proposes a new anomaly detection method based on an association-mining algorithm. The proposed method is composed of two phases: intra-packet association mining and inter-packet association mining. The performances of the proposed method are comparatively verified with JAM, which is a conventional representative intrusion detection method.

• Convergence Security Journal
• /
• v.11 no.1
• /
• pp.57-69
• /
• 2011

Many heterogeneous Intrusion Detection Systems(IDSs) based in misuse detection technique including the self-developed IDS are now operating in Defense-ESM(Enterprise Security Management System). IDS based on misuse detection may have different capability in the intrusion detection process according to the frequency and quality of its signature update. This makes the integration and collaboration with other IDSs more difficult. In this paper, with the purpose of creating the proper foundation for integration and collaboration between heterogeneous IDSs being operated in Defense-ESM, we propose an effective mechanism that can enable one IDS to propagate its new detection rules to other IDSs and receive updated rules from others. We also prove the performance of rule exchange and application possibility to defense environment through the implementation and experiment.

• 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.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.6
• /
• pp.531-536
• /
• 2002

In this paper, we have applied Genetic Algorithms(GAs) to Intrusion Detection System(TDS), and then proposed and simulated the misuse detection model firstly. We have implemented with the KBD contest data, and tried to simulated in the same environment. In the experiment, the set of record is regarded as a chromosome, and GAs are used to produce the intrusion patterns. That is, the intrusion rules are generated. We have concentrated on the simulation and analysis of classification among the Data Mining techniques and then the intrusion patterns are produced. The generated rules are represented by intrusion data and classified between abnormal and normal users. The different rules are generated separately from three models "Time Based Traffic Model", "Host Based Traffic Model", and "Content Model". The proposed system has generated the update and adaptive rules automatically and continuously on the misuse detection method which is difficult to update the rule generation. The generated rules are experimented on 430M test data and almost 94.3% of detection rate is shown.3% of detection rate is shown.

• Journal of Convergence Society for SMB
• /
• v.2 no.2
• /
• pp.1-6
• /
• 2012

In this paper, we propose a detector generation model which is applied to immune system to improve the misuse detection rates in misuse detection models. 10cv method is used to sendmail data which is provided by the DARPA. We experimented and analyzed the misuse detection rate that is either judgment of the normal system call as abnormal system call or judgment of the abnormal system call as normal system call. In the experiment, between detector which was generated by any abnormal system call and temporary detector. I did experiments with a new detector which was removed temporary detector which made a wrong decision for normal system call as an abnormal system call and abnormal system call as a normal system call. The misuse detection rate of detector which is applied to the immune system is greater than the other detector by 0.3%.

• Journal of Internet Computing and Services
• /
• v.7 no.3
• /
• pp.119-132
• /
• 2006

The network based security techniques well-known until now have week points to be passive in attacks and susceptible to roundabout attacks so that the misuse detection based intrusion prevention system which enables positive correspondence to the attacks of inline mode are used widely. But because the Misuse detection based Intrusion prevention system is proportional to the detection rules, it causes excessive false alarm and is linked to wrong correspondence which prevents the regular network flow and is insufficient to detect transformed attacks, This study suggests an Intrusion prevention system which uses Support Vector machines(hereinafter referred to as SVM) as one of rule based Intrusion prevention system and Anomaly System in order to supplement these problems, When this compared with existing intrusion prevention system, show performance result that improve about 20% and could through intrusion prevention system that propose false positive minimize and know that can detect effectively about new variant attack.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.5
• /
• pp.978-985
• /
• 2003

The implementation of abnormal behavior detection IDS is more difficult than the implementation of misuse behavior detection IDS because usage patterns are various. Therefore, most of commercial IDS is misuse behavior detection IDS. However, misuse behavior detection IDS cannot detect system intrusion in case of modified intrusion patterns occurs. In this paper, we apply data mining so as to detect intrusion with only audit data related in intrusion among many audit data. The agent in the distributed IDS can collect log data as well as monitoring target system. False positive should be minimized in order to make detection accuracy high, that is, core of intrusion detection system. So We apply data mining algorithm for prediction of modified intrusion pattern in the level of audit data learning.