• Smart Media Journal
• /
• v.11 no.11
• /
• pp.40-48
• /
• 2022

In this paper, an educational kit that can be used in AI education was developed to solve the difficulties of AI education. Through this, object detection and person detection in computer vision using CNN and OpenCV to learn practical-oriented experiences from theory-centered and user image recognition (Your Own) that learns and recognizes specific objects Image Recognition), user object classification (Segmentation) and segmentation (Classification Datasets), IoT hardware control that attacks the learned target, and Jetson Nano GPIO, an AI board, are developed and utilized to develop and utilize textbooks that help effective AI learning made it possible.

• Annual Conference of KIPS
• /
• 2011.04a
• /
• pp.1012-1015
• /
• 2011

IPv4 의 주소 고갈 문제를 해결하고 더 개선된 서비스를 제공하기 위해 IPv6 가 개발되었다. IPv4 와 달리 IPv6 는 보안을 고려하며 설계되어 기본적으로 IPSec 를 제공한다. 하지만 IPv6 에도 보안상의 취약점이 있어서 여러 공격과 보안 문제에 노출되어 있다. 그 중에서도 프라이버시 침해 문제가 존재하는데, 이 문제는 IPv6 에서 제공하는 주소 자동 설정 방식(Stateless address autoconfiguration)에서 발생한다. 이 주소 자동 설정 방식은 주소 공간의 효율적인 관리를 위해 제안되었다. 주소 자동 설정 방식에서 프라이버시 침해 문제가 발생하는데, 개인 식별 프라이버시와 위치 프라이버시로 분류할 수 있다. 본 논문에서는 프라이버시 위협과 그에 따른 해결 방안을 기술하고, 해결 방안에 따라 고려해야 할 사항들을 설명함으로써 프라이버시 침해 문제를 해결하는 데 도움을 주고자 한다.

• Journal of the Society of Disaster Information
• /
• v.19 no.4
• /
• pp.924-935
• /
• 2023

Purpose: The central aim of this study is to leverage machine learning techniques for the classification of Intrusion Detection System (IDS) data, with a specific focus on identifying the variables responsible for enhancing overall performance. Method: First, we classified 'R2L(Remote to Local)' and 'U2R (User to Root)' attacks in the NSL-KDD dataset, which are difficult to detect due to class imbalance, using seven machine learning models, including Logistic Regression (LR) and K-Nearest Neighbor (KNN). Next, we use the SHapley Additive exPlanation (SHAP) for two classification models that showed high performance, Random Forest (RF) and Light Gradient-Boosting Machine (LGBM), to check the importance of variables that affect classification for each model. Result: In the case of RF, the 'service' variable and in the case of LGBM, the 'dst_host_srv_count' variable were confirmed to be the most important variables. These pivotal variables serve as key factors capable of enhancing performance in the context of classification for each respective model. Conclusion: In conclusion, this paper successfully identifies the optimal models, RF and LGBM, for classifying 'R2L' and 'U2R' attacks, while elucidating the crucial variables associated with each selected model.

• Annual Conference of KIPS
• /
• 2007.11a
• /
• pp.1151-1153
• /
• 2007

P2P 및 Mobile Network, Reputations System 등의 분산 시스템은 sybil attack 에 노출되어 있다. sybil attack 은 한 명의 사용자가 다수의 식별자를 가진 것으로 위장하여 시스템 내에서 마치 실제 다수의 사용자인 양 시스템을 악용하는 공격방법이다. sybil attack 을 막기 위한 다양한 노력이 진행되었고, 최근에 SybilGuard 라는 social network 를 이용한 방어 방법이 제시되었다. SybilGuard 는 악의적인 사용자를 막기 위하여, Random Walk 의 변형이면서 결정적인 경로의 특징을 가지는 임의경로(Random Route)를 사용하여 악의적인 사용자의 sybil attack 을 방어한다. SybilGuard 는 sybil node 의 개수를 제한하고, 이들을 하나의 동일한 그룹으로 분류할 수 있도록 하여 시스템 내에서 가짜 식별자의 개수를 제한한다. 이를 위해 각 노드가 시스템에 돌어올 때 Verifier(V)노드가 이들 노드를 확인하게 되는데, 이를 위해 시스템 내의 선한 노드(Honest Node)를 사용하여 이들을 확인한다. 이 때, honest node 들은 verifier 의 요청에 따라 확인요청을 수행하게 되는데, social network 의 특성상 몇몇 노드들은 사회적인 명망으로 매우 큰 링크수를 가지게 될 것이며, 따라서 이들 노드들이 처리해야할 요청의 양이 매우 많아지게 될 것이다. 따라서 이들 honest node 들 간에 로드분포를 균등하게 하는 것이 요구되며, 이 논문에서는 부하 조절을 하기 위한 기법을 제시하고, 이들을 평가한다.

• Journal of Digital Contents Society
• /
• v.13 no.1
• /
• pp.101-110
• /
• 2012

Recently, social network sites are very popular with the enhancement of mobile device function and distribution. This gives rise to the registrations of the people on the social network sites and the usage of services on the social sites is also getting active. However, social network sites' venders do not provide services enough compared to the demand of users' to share contents from diverse roots by users effectively. In addition, the personal information can be revealed improperly in processes sharing policies and it is obvious that it raises a privacy invasion problem when users access the contents created from diverse devices according to the relationship by policies. However, the existing methods for the integration management of social network are weak to solve this problem. Thus, we propose a model to preserve user privacy, categorize contents efficiently, and give the access control permissions at the same time. In this paper, we encrypt policies and the trusted third party classifies the encrypted policies when the social network sites share the generated contents by users. In addition, the proposed model uses the RCBAC model to manage the contents generated by various devices and measures the similarity between relationships after encrypting when the user policies are shared. So, this paper can contribute to preserve user policies and contents from malicious attackers.

• Korean Journal of Biological Psychiatry
• /
• v.8 no.1
• /
• pp.20-36
• /
• 2001

The debate about whether depressive disorders should be divided into categories or arrayed along a continuum has gone for decade, without resolution. In our review, there is more evidence consistent with the spectrum concept than there is with the idea that depressive disorders constitute discrete clusters marked by relatively discontinuous boundaries. First, "depression spectrum", "is there a common genetic factors in bipolar and unipolar affective disorder", "threshold model of depression" and "bipolar spectrum disorder" are reviewed. And, a new subtype of depression is so called SeCA depression that is a stressor-precipitated, cortisol-induced, serotonin-related, anxiety/aggression-driven depression. SeCA depression is discussed. But, there is with the idea that depressive disorders constitute discrete subtypes marked by relatively discontinuous boundaries. This subtypes of depressive disorder were reviewed from a variety of theoretical frames of reference. The following issues are discussed ; Dexamethasone suppression test(DST), TRH stimulation test, MHPG, Temperament Character Inventory(TCI), and heart rate variability(HRV).

• Journal of Internet Computing and Services
• /
• v.21 no.1
• /
• pp.45-55
• /
• 2020

Due to the development of information and communication technology, the number of new / variant malicious codes is increasing rapidly every year, and various types of malicious codes are spreading due to the development of Internet of things and cloud computing technology. In this paper, we propose a malware analysis method based on string information that can be used regardless of operating system environment and represents library call information related to malicious behavior. Attackers can easily create malware using existing code or by using automated authoring tools, and the generated malware operates in a similar way to existing malware. Since most of the strings that can be extracted from malicious code are composed of information closely related to malicious behavior, it is processed by weighting data features using text mining based method to extract them as effective features for malware analysis. Based on the processed data, a model is constructed using various machine learning algorithms to perform experiments on detection of malicious status and classification of malicious groups. Data has been compared and verified against all files used on Windows and Linux operating systems. The accuracy of malicious detection is about 93.5%, the accuracy of group classification is about 90%. The proposed technique has a wide range of applications because it is relatively simple, fast, and operating system independent as a single model because it is not necessary to build a model for each group when classifying malicious groups. In addition, since the string information is extracted through static analysis, it can be processed faster than the analysis method that directly executes the code.

• Journal of Internet Computing and Services
• /
• v.20 no.6
• /
• pp.105-117
• /
• 2019

Bitcoin, which can be classified as a cryptocurrency, has attracted attention from various industries because it is an innovative digital currency and the beginning of a Blockchain system. However, as the research on Bitcoin progressed, several security vulnerabilities and possible attacks were analyzed. Among them, the security problem caused by the transparency of the Blockchain database prevents the Blockchain system from being applied to various fields. This vulnerability is further classified as the weak anonymity of participating nodes and privacy problem due to disclosure of transaction details. In recent years, several countermeasures have been developed against these vulnerabilities. In this paper, we first describe the main features of the public and private Blockchain, and explain privacy, unlinkability and anonymity. And, three public Blockchain platforms, Dash, Zcash and Monero which are derived from Bitcoin, and Hyperledger Fabric which is a private Blockchain platform, are examined. And we analyze the operating principles of the protocols applied on each platform. In addition, we classify the applied technologies into anonymity and privacy protection in detail, analyze the advantages and disadvantages, and compare the features and relative performance of the platforms based on the computational speed of the applied cryptographic mechanisms.

• Journal of the Korean Society of Child Welfare
• /
• no.56
• /
• pp.253-281
• /
• 2016

The purpose of this study was to verify the clinical utility of th Korea Child Behavior Checklist 16-18(K-CBCL 6-18) in diagnosing ADHD among children with psychological disorders in child welfare institutions. The participants were 509 elementary school children(309 boys and 200 girls) who lived in child welfare institutions. They were assessed using the Korean ADHD Rating Scale(K-ARS) and K-CBCL 6-18. Only five scales of the K-CBCL 6-18 related with attention were used for analysis: syndrom total, externalizing total, aggressive behavior, attention problems and DSM-oriented ADHD scales. The results were as follows. First, K-ARS and K-CBCL 6-18 had significantly positive correlations with all five scales. Second, as a result of a t-test on the ADHD and the non-ADHD groups, which were divided using K-ARS, the mean scores of ADHD group were significantly higher than the non-ADHD group for all five scales of the K-CBCL 6-18. The hit rate of all five scales of the K-CBCL 6-18 was 60 to 70 percent. The syndrom total and externalizing total scales had high sensitivity, whereas the aggressive behavior, attention problems, and the DSM-oriented ADHD scales had high specificity. In addition, all scales had high positive predictive values. Third, as the result of a t-test on the ADHD group and the emotional disorder group, there were significant difference in the mean scores of the attention problems and the DSM-oriented ADHD scales. The attention problems and the DSM-oriented ADHD scales had a similar percentage of hit rate, high specificity and low sensitivity. Especially, the DSM-oriented ADHD scale revealed higher specificity than the attention problems scale. The results of this study suggested that the five scales related to attention of the K-CBCL 6-18 are useful in diagnosing ADHD in child welfare institutions.

• The Korean Journal of Air & Space Law and Policy
• /
• v.26 no.2
• /
• pp.3-39
• /
• 2011

People may operate unmanned aerial vehicles (UAVs or drones) thousands of miles from the drone's location. Drones were first used (like balloons) for surveillance. By 2001, the United States began arming drones with missiles and using them to strike targets during combat in Afghanistan. By mid-2010, over forty states and other entities possessed drones, many with the capability of launching missiles and dropping bombs. Each new development in military weapons technology invites assessment of the relevant international law. This Insight surveys the international law applicable to the recent innovation of weaponizing drones. In determining what international law rules govern drone use, the most salient feature is not the fact that drones are unmanned. The fact drones carry no human operator may be the most important new technological breakthrough, but the key feature for international law purposes is the type of weaponry drones carry. Whether law enforcement rules govern drone use depends on the situation and not necessarily who is operating the drone. Battlefield weapons may also be lawfully used before an armed conflict in the following situations: when initiating self-defense under Article 51 of the United Nations Charter; when authorized by the UN Security Council; when a government seeks to suppress internal armed conflict; and, perhaps, when a state is invited to assist a government in suppressing internal armed conflict. The rules governing resort to force in self-defense are found in Article 51 of the UN Charter and a number of decisions by international courts and tribunals. Commentators continue to debate whether drone technology represents the next revolution in military affairs. Regardless of the answer to that question, drones have not created a revolution in legal affairs. The current rules governing battlefield launch vehicles are adequate for regulating resort to drones. More research must be undertaken, however, to understand the psychological effects of deploying unmanned vehicles and the effects on drone operators of sustained, close visual contact with the aftermath of drone attacks.