• Electronics and Telecommunications Trends
• /
• v.38 no.5
• /
• pp.71-80
• /
• 2023

With the rapid advancement of the Internet, the use of encrypted traffic has surged in order to protect data during transmission. Simultaneously, network attacks have also begun to leverage encrypted traffic, leading to active research in the field of encrypted traffic analysis to overcome the limitations of traditional detection methods. In this paper, we provide an overview of the encrypted traffic analysis field, covering the analysis process, domains, models, evaluation methods, and research trends. Specifically, it focuses on the research trends in the field of anomaly detection in encrypted network traffic analysis. Furthermore, considerations for model development in encrypted traffic analysis are discussed, including traffic dataset composition, selection of traffic representation methods, creation of analysis models, and mitigation of AI model attacks. In the future, the volume of encrypted network traffic will continue to increase, particularly with a higher proportion of attack traffic utilizing encryption. Research on attack detection in such an environment must be consistently conducted to address these challenges.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.25 no.5
• /
• pp.1043-1057
• /
• 2015

In order to recognize intelligent threats quickly and detect and respond to them actively, major public bodies and private institutions operate and administer an Intrusion Detection Systems (IDS), which plays a very important role in finding and detecting attacks. However, most IDS alerts have a problem that they generate false positives. In addition, in order to detect unknown malicious codes and recognize and respond to their threats in advance, APT response solutions or actions based systems are introduced and operated. These execute malicious codes directly using virtual technology and detect abnormal activities in virtual environments or unknown attacks with other methods. However, these, too, have weaknesses such as the avoidance of the virtual environments, the problem of performance about total inspection of traffic and errors in policy. Accordingly, for the effective detection of intrusion, it is very important to enhance security monitoring, consequentially. This study discusses a plan for the reduction of false positives as a plan for the enhancement of security monitoring. As a result of an experiment based on the empirical data of G, rules were drawn in three types and 11 kinds. As a result of a test following these rules, it was verified that the overall detection rate decreased by 30% to 50%, and the performance was improved by over 30%.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.04a
• /
• pp.971-974
• /
• 2011

본 논문에서는 대용량 네트워크에 비정상적인 트래픽이 유입이 되거나 나가는 경우 패킷 기반의 비정상 트래픽의 탐지와 분석이 가능토록 하는 시스템을 설계하고 구현하였다. 본 논문에서 구현한 시스템은 네트워크상의 이상 행위를 탐지하기 위하여, DDoS HTTP Get Flooding 공격 탐지 알고리즘을 적용하고, NetFPGA를 이용하여 라우터 단에서 패킷을 모니터링하며 공격을 탐지한다. 본 논문에서 구현한 시스템은 Incomplete Get 공격 타입의 Slowloris 봇과, Attack Type-2 공격 타입의 BlackEnergy, Netbot Vip5.4 봇에 높은 탐지율을 보였다.

• Journal of Internet of Things and Convergence
• /
• v.5 no.2
• /
• pp.95-101
• /
• 2019

Entering the era of the 4^th Industrial Revolution and the Internet of Things, various services are growing rapidly, and various researches are actively underway. Among them, research on abnormal behaviors on various devices that are being used in the IoT is being conducted. In a hyper-connected society, the damage caused by one wrong device can have a serious impact on the various connected systems. In this paper, We propose a technique to cope with the problem that the threats caused by various abnormal behaviors such as anti-debugging scheme, anomalous process detection method and back door detection method on how to increase the safety of the device and how to use the device and service safely in such IoT environment.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.48 no.5
• /
• pp.25-30
• /
• 2011

This paper present a method for abnormal traffic behavior, or trajectory, detection in static traffic surveillance camera with user-defined trajectories. The method computes the abnormality of moving object with a trajectory of the object and user-defined trajectories. Because of using user-define based information, the presented method have more accurate and faster performance than models need a learning about normal behaviors. The method also have adaptation process of assigned rule, so it can handle scene variation for more robust performance. The experimental results show that our method can detect abnormal traffic behaviors in various situation.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.15 no.2
• /
• pp.13-22
• /
• 2005

To improve the anomaly IDS using system calls, this study focuses on Neural Networks Learning using the Soundex algorithm which is designed to change feature selection and variable length data into a fixed length learning pattern. That is, by changing variable length sequential system call data into a fixed length behavior pattern using the Soundex algorithm, this study conducted neural networks learning by using a backpropagation algorithm with fuzzy membership function. The back-propagation neural networks and Neuro-Fuzzy technique are applied for anomaly intrusion detection of system calls using Sendmail Data of UNM to demonstrate its aspect of he complexity of time, space and MDL performance.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.10
• /
• pp.1311-1319
• /
• 2019

Currently, the web environment is a commonly used area for sharing information and conducting business. It is becoming an attack point for external hacking targeting on personal information leakage or system failure. Conventional signature-based detection is used in cyber threat but signature-based detection has a limitation that it is difficult to detect the pattern when it is changed like polymorphism. In particular, injection attack is known to the most critical security risks based on web vulnerabilities and various variants are possible at any time. In this paper, we propose a novelty detection technique to detect abnormal state that deviates from the normal state on web-server log dataset(WSLD). The proposed method is a machine learning-based technique to detect a minor anomalous data that tends to be different from a large number of normal data after replacing strings in web-server log dataset with vectors using machine learning-based embedding algorithm.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06d
• /
• pp.97-100
• /
• 2008

PDoS (Path-based DoS) 공격은 J. Deng에 의해 처음 소개된 DoS 공격의 하나이다. PDoS 공격은 Base Station을 향해 대량의 bogus 패킷을 경로상에 플러딩하여 경로상에 있는 중간 노드들의 배터리 파워를 빠르게 소모를 시켜 수명을 단축시킨다. 그 결과 경로상의 중간 노드들은 수명을 마치게 되어 경로가 마비시켜 전체적으로 네트워크를 마비시킨다. 이런 PDoS 공격을 탐지하기 위해 J. Deng의 one-way hash function을 이용한 탐지방식은 매우 효율적이다. 하지만 공격자가 compromised node을 사용할 경우 이 탐지 기법은 소용이 없어진다. compromised node는 특성상 특별하게 눈에 띄는 비정상 행위를 하지 않는 이상 일반 노드와 구분하기가 힘들며 공격자에 의해 다른 여러 공격에 이용되어 무선 센서 네트워크 보안에 큰 위협이 된다. 이에 본 논문에서는 무선 센서 네트워크상에서 PDoS 공격을 야기하는 compromised node를 탐지하는 방법을 제안한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2001.10a
• /
• pp.523-526
• /
• 2001

최근 컴퓨터와 인터넷의 급속한 발전과 더불어 컴퓨터의 데이터를 파괴하거나 바이러스를 이용해 정보를 빼내기 위한 해킹 등이 만연하고 있다. 이에 컴퓨터의 데이터를 외부 침입물질에 대해 자체적인 보호와 제거 기능을 가진 생체 면역시스템을 이용한 연구가 활발히 진행되고 있다. 생체 면역 시스템은 바이러스나 병원균 등의 낮선 외부의 침입자로부터 자신을 보호하기 위해 크게 선천성 면역과 후천성 면역을 제공한다. 본 논문은 선천성 면역에는 오용탐지기법과 후천성 면역에는 비정상행위 탐지 기법을 이용한 하이브리드 침입탐지 시스템을 제안한다. 감사 자료 수집은 멀티레벨 파라미터 모니터링을 통해 감사 자료를 수집한다. 선천성 면역에서는 피부와 여러 가지 감각 기관의 분비물을 이용하듯이 방화벽과 같은 비슷한 기능을 하는 서비스 제한 에이전트와 기존에 알려진 버그와 해킹 기법을 시나리오 지식베이스를 이용하는 오용탐지 기법을 사용한다. 그리고, 후천성 면역에서는 유전자 알고리즘을 이용해 침입을 탐지하고 대응한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06b
• /
• pp.124-129
• /
• 2008

독거노인의 수가 증가함에 따라 노인의 건강한 생활 패턴 유지 및 응급상황탐지 등을 위해 생활모니터링에 대한 연구가 요구되고 있다. 본 논문에서는 단순히 사물에 대한 접촉만으로 일상생활행위(ADL : activity of daily living)를 인식하기 보다는 노인의 행동과 연관이 있는 사물의 접촉을 함께 고려한 행위인 요소ADL를 인식하여 정확하게 최종 ADL를 인식할 수 있도록 한다. 또한, 행위센서로부터 인식된 물리적 행위분류는 간혹 튀는 데이터들로 인해 잘못된 결과가 나오므로, 이를 보정함으로써 인식의 정확성을 더 보장한다. 실험결과는 8개의 요소ADL에 대해 97% 이상의 인식 결과를 보이며, 이는 최종 ADL을 인식하는데 효율적으로 적용할 수 있음을 보인다.