• The KIPS Transactions:PartC
• /
• v.12C no.5 s.101
• /
• pp.649-658
• /
• 2005

Since the Network based attack Is extensive in the real state of damage, It is very important to detect intrusion quickly at the beginning. But the intrusion detection using supervised learning needs either the preprocessing enormous data or the manager's analysis. Also it has two difficulties to detect abnormal traffic that the manager's analysis might be incorrect and would miss the real time detection. In this paper, we propose a traffic attributes correlation analysis mechanism based on self-organizing maps(SOM) for the real-time intrusion detection. The proposed mechanism has three steps. First, with unsupervised learning build a map cluster composed of similar traffic. Second, label each map cluster to divide the map into normal traffic and abnormal traffic. In this step there is a rule which is created through the correlation analysis with SOM. At last, the mechanism would the process real-time detecting and updating gradually. During a lot of experiments the proposed mechanism has good performance in real-time intrusion to combine of unsupervised learning and supervised learning than that of supervised learning.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.4
• /
• pp.617-629
• /
• 2020

In order to overcome the limitations of the rule-based intrusion detection system due to changes in Internet computing environments, the emergence of new services, and creativity of attackers, network anomaly detection (NAD) using machine learning and deep learning technologies has received much attention. Most of these existing machine learning and deep learning technologies for NAD use supervised learning methods to learn a set of training data set labeled 'normal' and 'attack'. This paper presents the feasibility of the unsupervised learning AutoEncoder(AE) to NAD from data sets collecting of secured network traffic without labeled responses. To verify the performance of the proposed AE mode, we present the experimental results in terms of accuracy, precision, recall, f1-score, and ROC AUC value on the NSL-KDD training and test data sets. In particular, we model a reference AE through the deep analysis of diverse AEs varying hyper-parameters such as the number of layers as well as considering the regularization and denoising effects. The reference model shows the f1-scores 90.4% and 89% of binary classification on the KDDTest+ and KDDTest-21 test data sets based on the threshold of the 82-th percentile of the AE reconstruction error of the training data set.

• The KIPS Transactions:PartC
• /
• v.17C no.1
• /
• pp.1-14
• /
• 2010

IEEE 802.15.4[1] has been standardized for the physical layer and MAC layer of LR-PANs(Low Rate-Wireless Personal Area Networks) as a technology for operations with low power on sensor networks. The standardization is applied to the variety of applications in the shortrange wireless communication with limited output and performance, for example wireless sensor or virtual wire, but it includes vulnerabilities for various attacks because of the lack of security researches. In this paper, we analyze the vulnerabilities against the denial of sleep attacks on the MAC layer of IEEE 802.15.4, and propose a detection mechanism against it. In results, we analyzed the possibilities of denial of sleep attacks by the modification of superframe, the modification of CW(Contention Window), the process of channel scan or PAN association, and so on. Moreover, we comprehended that some of these attacks can mount even though the standardized security services such as encryption or authentication are performed. In addition to, we model for denial of sleep attacks by Beacon/Association Request messages, and propose a detection mechanism against them. This detection mechanism utilizes the management table consisting of the interval and node ID of request messages, and signal strength. In simulation results, we can show the effect of attacks, the detection possibility and performance superiorities of proposed mechanism.

• Journal of Radiation Protection and Research
• /
• v.34 no.3
• /
• pp.115-120
• /
• 2009

Since 1990s, some events - detection of a dirty bomb in a Russian nation park in 1995, 9/11 terrorist attack to WTC in 2001, discovery of Al-Qaeda's experimentation to build a dirty bomb in 2003 etc - have showed that nuclear or radiological terrorism relating to radioactive materials (hereinafter "radioactive materials" is referred to as "nuclear material, nuclear spent fuel and radioactive source") is not incredible but serious and credible threat. Thus, to respond to the new threat, the international community has not only strengthened security and physical protection of radioactive materials but also established prevention of and response to illicit trafficking of radioactive materials. In this regard, our government has enacted or revised the national regulatory framework with a view to improving security of radioactive materials and joined the international convention or agreement to meet this international trend. For the purpose of prevention of nuclear/radiological terrorism, this paper reviews physical characteristics of nuclear material and existing detection instruments used for prevention of illicit trafficking. Finally, national detection regime against nuclear/radiological terrorism based on paths of the smuggled radioactive materials to terrorist's target building/area, national topography and road networks, and defence-in-depth concept is suggested in this paper. This study should contribute to protect people's health, safety and environment from nuclear/radiological terrorism.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.7
• /
• pp.271-278
• /
• 2021

As the current cyber attacks become more intelligent, the existing Intrusion Detection System is difficult for detecting intelligent attacks that deviate from the existing stored patterns. In an attempt to solve this, a model of a deep learning-based intrusion detection system that analyzes the pattern of intelligent attacks through data learning has emerged. Intrusion detection systems are divided into host-based and network-based depending on the installation location. Unlike network-based intrusion detection systems, host-based intrusion detection systems have the disadvantage of having to observe the inside and outside of the system as a whole. However, it has the advantage of being able to detect intrusions that cannot be detected by a network-based intrusion detection system. Therefore, in this study, we conducted a study on a host-based intrusion detection system. In order to evaluate and improve the performance of the host-based intrusion detection system model, we used the host-based Leipzig Intrusion Detection-Data Set (LID-DS) published in 2018. In the performance evaluation of the model using that data set, in order to confirm the similarity of each data and reconstructed to identify whether it is normal data or abnormal data, 1D vector data is converted to 3D image data. Also, the deep learning model has the drawback of having to re-learn every time a new cyber attack method is seen. In other words, it is not efficient because it takes a long time to learn a large amount of data. To solve this problem, this paper proposes the Siamese Convolutional Neural Network (Siamese-CNN) to use the Few-Shot Learning method that shows excellent performance by learning the little amount of data. Siamese-CNN determines whether the attacks are of the same type by the similarity score of each sample of cyber attacks converted into images. The accuracy was calculated using Few-Shot Learning technique, and the performance of Vanilla Convolutional Neural Network (Vanilla-CNN) and Siamese-CNN was compared to confirm the performance of Siamese-CNN. As a result of measuring Accuracy, Precision, Recall and F1-Score index, it was confirmed that the recall of the Siamese-CNN model proposed in this study was increased by about 6% from the Vanilla-CNN model.

• Journal of Internet Computing and Services
• /
• v.15 no.3
• /
• pp.79-90
• /
• 2014

User authentication based on ID and PW has been widely used. As the Internet has become a growing part of people' lives, input times of ID/PW have been increased for a variety of services. People have already learned enough to perform the authentication procedure and have entered ID/PW while ones are unconscious. This is referred to as the adaptive unconscious, a set of mental processes incoming information and producing judgements and behaviors without our conscious awareness and within a second. Most people have joined up for various websites with a small number of IDs/PWs, because they relied on their memory for managing IDs/PWs. Human memory decays with the passing of time and knowledges in human memory tend to interfere with each other. For that reason, there is the potential for people to enter an invalid ID/PW. Therefore, these characteristics above mentioned regarding of user authentication with ID/PW can lead to human vulnerabilities: people use a few PWs for various websites, manage IDs/PWs depending on their memory, and enter ID/PW unconsciously. Based on the vulnerability of human factors, a variety of information leakage attacks such as phishing and pharming attacks have been increasing exponentially. In the past, information leakage attacks exploited vulnerabilities of hardware, operating system, software and so on. However, most of current attacks tend to exploit the vulnerabilities of the human factors. These attacks based on the vulnerability of the human factor are called social-engineering attacks. Recently, malicious social-engineering technique such as phishing and pharming attacks is one of the biggest security problems. Phishing is an attack of attempting to obtain valuable information such as ID/PW and pharming is an attack intended to steal personal data by redirecting a website's traffic to a fraudulent copy of a legitimate website. Screens of fraudulent copies used for both phishing and pharming attacks are almost identical to those of legitimate websites, and even the pharming can include the deceptive URL address. Therefore, without the supports of prevention and detection techniques such as vaccines and reputation system, it is difficult for users to determine intuitively whether the site is the phishing and pharming sites or legitimate site. The previous researches in terms of phishing and pharming attacks have mainly studied on technical solutions. In this paper, we focus on human behaviour when users are confronted by phishing and pharming attacks without knowing them. We conducted an attack experiment in order to find out how many IDs/PWs are leaked from pharming and phishing attack. We firstly configured the experimental settings in the same condition of phishing and pharming attacks and build a phishing site for the experiment. We then recruited 64 voluntary participants and asked them to log in our experimental site. For each participant, we conducted a questionnaire survey with regard to the experiment. Through the attack experiment and survey, we observed whether their password are leaked out when logging in the experimental phishing site, and how many different passwords are leaked among the total number of passwords of each participant. Consequently, we found out that most participants unconsciously logged in the site and the ID/PW management dependent on human memory caused the leakage of multiple passwords. The user should actively utilize repudiation systems and the service provider with online site should support prevention techniques that the user can intuitively determined whether the site is phishing.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.9 no.2
• /
• pp.196-204
• /
• 2016

World Health Organization reported that heart-related diseases such as coronary artery stenoses show the highest occurrence rate which may cause heart attack. Using Computed Tomography angiography images will allow radiologists to detect and have intervention by creating 3D roadmapping of the vessels. However, it is often complex and difficult do reconstruct 3D vessel which causes very large amount of time and previous researches were studied to segment vessels more accurate automatically. Therefore, in this paper, Region Competition, Geodesic Active Contour (GAC), Multi-atlas based segmentation and Active Shape Model algorithms were applied to segment aortic root from CTA images and the results were analyzed by using mean Hausdorff distance, volume to volume measure, computational time, user-interaction and coronary ostium detection rate. As a result, Extracted 3D aortic model using GAC showed the highest accuracy but also showed highest user-interaction results. Therefore, it is important to improve automatic segmentation algorithm in future

• Journal of Digital Contents Society
• /
• v.19 no.4
• /
• pp.837-844
• /
• 2018

Recently, the cloud technology has made dynamical network changes by enabling the construction of a logical network without building a physical network. Despite recent research on the cloud, it is necessary to study security functions for the identification of fake virtual network functions and the encryption of communication between entities. Because the VNFs are open to subscribers and able to implement service directly, which can make them an attack target. In this paper, we propose a virtual public key infrastructure mechanism that detects a fake VNFs and guarantees data security through mutual authentication between VNFs. To evaluate the virtual PKI, we built a management and orchestration environment to test the performance of authentication and key generation for data security. And we test the detection of a distributed denial of service by using several AI algorithms to enhance the security in NFV.

• KIISE Transactions on Computing Practices
• /
• v.24 no.2
• /
• pp.99-104
• /
• 2018

Recently, there are increasing damages by ransomware in the world. Ransomware is a malicious software that infects computer systems and restricts user's access to them by locking the system or encrypting user's files saved in the hard drive. Victims are forced to pay the 'ransom' to recover from the damage and regain access to their personal files. Strong countermeasure is needed due to the extremely vicious way of attack with enormous damage. Malware analysis method can be divided into two approaches: static analysis and dynamic analysis. Recent malwares are usually equipped with elaborate packing techniques which are main obstacles for static analysis of malware. Therefore, this paper suggests a dynamic analysis method to monitor activities of ransomware. The proposed method can analyze ransomwares more accurately. The suggested method is comprised of extracting signatures of benign program, malware, and ransomware, and selecting the most appropriate signatures for ransomware detection.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.5
• /
• pp.1169-1177
• /
• 2018

Modern society is a period of rapid digital transformation. This digital-centric business proliferation offers convenience and efficiency to businesses and individuals, but cyber threats are increasing. In particular, cyber attacks are becoming more and more intelligent and precise, and various attempts have been made to prevent these attacks from being discovered. Therefore, it is increasingly difficult to respond to such attacks. According to the cyber kill chain concept, the attacker penetrates to achieve the goal in several stages. We aim to detect one of these stages and neutralize the attack. In this paper, we propose a method to detect anomalous traffic caused by an agent attacking an external attacker, assuming that an agent executing a malicious action has been introduced in advance due to various reasons such as a system error or a user's mistake.