• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.8 no.4
• /
• pp.316-321
• /
• 2008

Advanced computer network technology enables computers to be connected in an open network environment. Despite the growing numbers of security threats to networks, most intrusion detection identifies security attacks mainly by detecting misuse using a set of rules based on past hacking patterns. This pattern matching has a high rate of false positives and can not detect new hacking patterns, which makes it vulnerable to previously unidentified attack patterns and variations in attack and increases false negatives. Intrusion detection and analysis technologies are thus required. This paper investigates the asymmetric costs of false errors to enhance the performances the detection systems. The proposed method utilizes the network model to consider the cost ratio of false errors. By comparing false positive errors with false negative errors, this scheme achieved better performance on the view point of both security and system performance objectives. The results of our empirical experiment show that the network model provides high accuracy in detection. In addition, the simulation results show that effectiveness of anomaly traffic detection is enhanced by considering the costs of false errors.

• 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.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.11
• /
• pp.4553-4562
• /
• 2010

With developing networks, information security is going to be important and therefore lots of intrusion detection system has been developed. Intrusion detection system has abilities to detect abnormal behavior and unknown intrusions also it can detect intrusions by using patterns studied from various penetration methods. Various algorithms are studying now such as the statistical method for detecting abnormal behavior, extracting abnormal behavior, and developing patterns that can be expected. Etc. This study using clustering of data mining and association rule analyzes detecting areas based on two models and helps design detection system which detecting abnormal behavior, unknown attack, misuse attack in a large network.

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2005.11a
• /
• pp.161-164
• /
• 2005

As the power of influence of the Internet grows steadily, attacks against the Internet can cause enormous monetary damages nowadays. A worm can not only replicate itself like a virus but also propagate itself across the Internet. So it infects vulnerable hosts in the Internet and then downgrades the overall performance of the Internet or makes the Internet not to work. To response this, worm detection and prevention technologies are developed. The worm detection technologies are classified into two categories, host based detection and network based detection. Host based detection methods are a method which checks the files that worms make, a method which checks the integrity of the file systems and so on. Network based detection methods are a misuse detection method which compares traffic payloads with worm signatures and anomaly detection methods which check inbound/outbound scan rates, ICMP host/port unreachable message rates, and TCP RST packet rates. However, single detection methods like the aforementioned can't response worms' attacks effectively because worms attack the Internet in the distributed fashion. In this paper, we propose a design of distributed worm detection system to overcome the inefficiency. Existing distributed network intrusion detection systems cooperate with each other only with their own information. Unlike this, in our proposed system, a worm detection system on a network in which worms select targets and a worm detection system on a network in which worms propagate themselves cooperate with each other with the direction-aware information in terms of worm's lifecycle. The direction-aware information includes the moving direction of worms and the service port attacked by worms. In this way, we can not only reduce false positive rate of the system but also prevent worms from propagating themselves across the Internet through dispersing the confirmed worm signature.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.13 no.5
• /
• pp.91-104
• /
• 2003

A masquerader is someone who pretends to be another user while invading the target user's accounts, directories, or files. The masquerade attack is the most serious computer misuse. Because, in most cases, after securing the other's password, the masquerader enters the computer system. The system such as IDS could not detect or response to the masquerader. The masquerade detection is the effort to find the masquerader automatically. This system will detect the activities of a masquerader by determining that user's activities violate a profile developed for that user with his audit data. From 1988, there are many efforts on this topic, but the success of the offers was limited and the performance was unsatisfactory. In this report we propose efficient masquerade detection system using SVM which create the user profile.

• Proceedings of the Korea Institutes of Information Security and Cryptology Conference
• /
• 2001.11a
• /
• pp.153-156
• /
• 2001

Code Red, Nimda 등 최근 인터넷웜(Internet Worm)에 의한 침입은 방화벽시스템, 침입탐지시스템 등 보안제품이 존재하는 네트워크에서도 적절한 대책이 되지 않은 경향을 보이고 있다. 침입차단시스템을 통과할 수 있는 신종 취약점을 이용한 침입에는 오용방지방법(Misuse Detection)에 의한 침입탐지시스템이 침입패턴을 업데이트하기 전에 이미 네트 워크에 피해를 입힐 가능성이 크게 증가하는 것이다. 향후에도 크게 증가할 것으로 보이는 인터넷웜 공격 등에는 침입차단시스템, 침입탐지시스템 등 보안제품의 로그기록 상황과 네트워크의 보안상태를 지속적으로 감시함으로서 조기에 침입을 탐지할 수 있다. 본 논문에서는 신종 웜 공격에 의한 침입이 발생되었을 때 IDS가 탐지하지 못하는 상황에서도 침입의 흔적을 조기에 발견할 수 있는 네트워크 보안 상태변수확인방법(Network Security Parameter Matching Method)을 제안하고자 한다.

• The KIPS Transactions:PartC
• /
• v.9C no.6
• /
• pp.831-840
• /
• 2002

Due to the advance of computer and communication technology, intrusions or crimes using a computer have been increased rapidly while tremendous information has been provided to users conveniently Specially, for the security of a database which stores important information such as the private information of a customer or the secret information of a company, several basic suity methods of a database management system itself or conventional misuse detection methods have been used. However, a problem caused by abusing the authority of an internal user such as the drain of secret information is more serious than the breakdown of a system by an external intruder. Therefore, in order to maintain the sorority of a database effectively, an anomaly defection technique is necessary. This paper proposes a method that generates the normal behavior profile of a user from the database log of the user based on an association mining method. For this purpose, the Information of a database log is structured by a semantically organized pattern tree. Consequently, an online transaction of a user is compared with the profile of the user, so that any anomaly can be effectively detected.

• Convergence Security Journal
• /
• v.7 no.4
• /
• pp.35-41
• /
• 2007

In accordance with increasing of digital contents and rising of property value, the importance of storing equipment system which can store and control essential contents has been maximized, and securer storing equipment system overcoming various vulnerabilities is now required. Therefore, in this paper, we analyzed misuse, abuse, modification, leak, and various vulnerabilities of storing equipment system that might be damaged, and we researched into an intrusion detection & recovery system which can solve potential vulnerabilities.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.06a
• /
• pp.315-329
• /
• 2001

외부침입탐지 시스템(IDS: Intrusion Detection System)은 컴퓨터의 외부 침입을 자동으로 탐지하는 시스템이다. IDS의 주요목표는 외부사용자들이나 내부 사용자들에서 권한이 없는 사용자, 컴퓨터 오용(misuse) 혹은 잘못된 사용(abuse)을 탐지하는 것이다. 파이어 월(Firewall)이나 암호화와 같은 침입 방지 시스템에 관한 연구와 병행하여 최근 IDS에 대한 다양한 연구가 이루어지고 있다. 침입탐지와 바이러스 탐지에 대한 새로운 접근 방법으로서 면역학적 방법이 동원되고 있다. 이 연구에서는 인간의 인체면역 시스템으로부터 얻어진 몇 가지 주요한 Feature들을 외부침입 탐지에 적용하여 기존의 침입탐지 방법에서 오는 한계점을 극복하여 경고 오류(alarm error rate)를 줄이고자 한다. 따라서 본 연구에서는 외부침입을 탐지하고 시스템을 치유하는 인간의 인체 면역에 대해 기초적인 연구를 진행하였으며 이러한 인체면역 기저들을 네트워크 환경에서 어떻게 실제적으로 적용할 것인 지를 연구하였으며 실제 네트워크 데이터를 적용하여 본 연구에서 제안한 모델에 대한 성능을 테스트하였다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.2
• /
• pp.169-174
• /
• 2003

The trial and success of malicious cyber attacks has been increased rapidly with spreading of Internet and the activation of a internet shopping mall and the supply of an online, or an offline internet, so it is expected to make a problem more and more. The goal of intrusion detection is to identify unauthorized use, misuse, and abuse of computer systems by both system insiders and external penetrators in real time. In fact, the general security system based on Internet couldn't cope with the attack properly, if ever. other regular systems have depended on common vaccine softwares to cope with the attack. But in this paper, we will use the positive selection and negative selection mechanism of T-cell, which is the biologically distributed autonomous system, to develop the self/nonself recognition algorithm and AIS (Artificial Immune System) that is easy to be concrete on the artificial system. For making it come true, we will apply AIS to the network environment, which is a computer security system.