Design and Implementation of Geo-Social Information based Personalized Warning Notification System

김경백,Duc, Tiep Vu,Nguyen-Van, Quyet,Kim, Kyungbaek 한국스마트미디어학회 2016 스마트미디어저널 Vol.5 No.2

In case of a emergency situation or a natural disaster, a warning notification system is an essential tool to notify at-risk people in advance and provide them useful information to survive the event. Although some systems have been proposed such as emergency alert system using android, SMS, or P2P overlay network, these works mainly focus on a reliable message distribution methods. In this paper, we proposed a novel design and implementation of a personalized warning notification system to help inform not only the at-risk people but also their family and friends about the coming disaster as well as escape plan and survival information. The system consists of three main modules: the user selection module, the knowledge based message generator, and message distribution modules. The user selection module collects the list of people involved in the event and sorts them based on their level of involvement (their location, working position and social relationships). The knowledge based message generator provides each person with a personalized message that is concise and contains only the necessary information for the particular person based on their working position and their involvement in the event. The message distribution module will then find a best path for sending the personalized messages based on trustiness of locations since network failures may exist in a disaster event. Additionally, the system also have a comprehensive database and an interactive web interface for both user and system administrator. For evaluation, the system was implemented and demonstrated successfully with a building on fire scenario.

OSN 기반 Sybil-resistant trust value 추출 기법들에 대한 성능평가

김경백 ( Kyungbaek Kim ) 한국정보처리학회 2013 한국정보처리학회 학술대회논문집 Vol.20 No.1

인터넷상에서 다양한 사용자 및 구성요소로 이루어진 분산시스템은 Sybil Attack 에 취약하다. 최근 온라인 소셜 네트워크(Online Social Network)의 그래프 정보를 사용해, Sybil Attack 에 대응하기 위한 Sybil-resistant value 추출 기법들이 제안되었다. 이 논문에서는 이러한 OSN 기반의 Sybil-resistant value 추출 기법들에 대한 성능을 평가한다. 특히 OSN 그래프의 각 노드들의 이웃 노드 개수 정보에 따른 성능과 Sybil 노드들의 Attack Edge 에 따른 성능을 평가한다. Facebook 에서 추출한 샘플 OSN 그래프를 사용한 성능 평가 분석을 통해, 실제 사용자를 위한 Sybil-resistant value 를 정상적으로 추출하기 위해서는 OSN 그래프 상에서 이웃 노드의 개수가 10 개 이상이어야 한다는 점과, Random Route Tail Intersection 기법이 Sybil 사용자 그룹의 Attack Edge 의 영향을 가장 적게 받는 다는 점을 확인 하였다.

온라인 소셜 네트워크 그래프에 내포된 시스템-차원 시빌-저항 신뢰도 추출

김경백 ( Kyungbaek Kim ) 한국정보처리학회 2013 정보처리학회논문지. 컴퓨터 및 통신시스템 Vol.2 No.12

Anonymity is the one of main reasons for substantial improvement of Internet. It encourages various users to express their opinion freely and helps Internet based distributed systems vitalize. But, anonymity can cause unexpected threats because personal information of an online user is hidden. Especially, distributed systems are threatened by Sybil attack, where one malicious user creates and manages multiple fake online identities. To prevent Sybil attack, the traditional solutions include increasing the complexity of identity generation and mapping online identities to real-world identities. But, even though the high complexity of identity generation increases the generation cost of Sybil identities, eventually they are generated and there is no further way to suppress their activity. Also, the mapping between online identities and real identities may cause high possibility of losing anonymity. Recently, some methods using online social network to prevent Sybil attack are researched. In this paper, a new method is proposed for extracting a user`s system-wide Sybil-resistant trust value by using the properties embedded in online social network graphs. The proposed method can be categorized into 3 types based on sampling and decision strategies. By using graphs sampled from Facebook, the performance of the 3 types of the proposed method is evaluated. Moreover, the impact of Sybil attack on nodes with different characteristics is evaluated in order to understand the behavior of Sybil attack.

이더리움 스마트 컨트랙트 보안 취약점 분석 및 대응방안에 대한 연구

김현준(Hyunjun Kim),오석환(Seokhwan Oh),김구민(Gumin Kim),김휘수(Hwi Soo Kim),송효준(Hyojun Song),하태균(Taegyun Ha),김경백(Kyungbaek Kim) 한국통신학회 2023 한국통신학회 학술대회논문집 Vol.2023 No.2

S-BERT 를 사용하는 파킨슨병 탐지에 대한 데이터 증강 기술 영향 탐구

MdIliasBappi,김경백 ( Kyungbaek Kim ) 한국정보처리학회 2025 한국정보처리학회 학술대회논문집 Vol.32 No.1

모바일 사용자를 위한 Q+R 트리 기반 퍼브-서브 시스템

이명국,김경백,Lee, Myung-Guk,Kim, Kyungbaek 한국스마트미디어학회 2015 스마트미디어저널 Vol.4 No.3

A pub(lish)/sub(scribe) system is a data forwarding system which forwards only interesting data among the whole published data, which is related to the subscriptions registered by end users. Classical pub/sub systems are realized by constructing a network of brokers which are responsible for storing or forwarding data. Along with the substantial increase of the population mobile users, it is required that the pub/sub system handles the subscriptions of user locations which changes continuously and frequently. In this paper, a new broker network based pub/sub system which efficiently handles the frequent changes of subscriptions related to user locations is proposed. In consideration of moving patterns of users and geographical property, the proposed pub/sub system categorize the entire data space into Slow Moving Region and Normal Moving Region, and manages the brokers which are responsible for these regions by using Q+R tree in order to handle user requests more efficiently. Through the extensive simulation, it is presented that the proposed Q+R tree based pub/sub system can reduce unnecessary needs of brokers and network traffic and can support the dynamic subscription related to user location.

스마트 컨트랙트 개발 보안 권장사항에 대한 연구

김현준 ( Hyunjun Kim ),박소현 ( Sohyeon Park ),이강효 ( Kanghyo Lee ),하태균 ( Taegyun Ha ),김경백 ( Kyungbaek Kim ) 한국정보처리학회 2023 한국정보처리학회 학술대회논문집 Vol.30 No.1

Assessing the Relationship between MBTI User Personality and Smartphone Usage

라저스리 소카세인,김경백,Rajashree, Sokasane S.,Kim, Kyungbaek Korea Bigdata Society 2016 한국빅데이터학회 학회지 Vol.1 No.1

Recently, predicting personality with the help of smartphone usage becomes very interesting and attention grabbing topic in the field of research. At present there are some approaches towards detecting a user's personality which uses the smartphones usage data, such as call detail records (CDRs), the usage of short message services (SMSs) and the usage of social networking services application. In this paper, we focus on the assessing the correlation between MBTI based user personality and the smartphone usage data. We used $Na{\ddot{i}}ve$ Bayes and SVM classifier for classifying user personalities by extracting some features from smartphone usage data. From analysis it is observed that, among all extracted features facebook usage log working as the best feature for classification of introverts and extraverts; and SVM classifier works well as compared to $Na{\ddot{i}}ve$ Bayes.

2D-CNN 모델을 이용한 메타-전이학습 기반 부정맥 분류

김아현 ( Ahyun Kim ),염성웅 ( Sunhwoong Yeom ),김경백 ( Kyungbaek Kim ) 한국정보처리학회 2022 한국정보처리학회 학술대회논문집 Vol.29 No.2

최근 사물인터넷(IoT) 기기가 활성화됨에 따라 웨어러블 장치 환경에서 장기간 모니터링 및 수집이 가능해짐에 따라 생체 신호 처리 및 ECG 분석 연구가 활성화되고 있다. 그러나, ECG 데이터는 부정맥 비트의 불규칙적인 발생으로 인한 클래스 불균형 문제와 근육의 떨림 및 신호의 미약등과 같은 잡음으로 인해 낮은 신호 품질이 발생할 수 있으며 훈련용 공개데이터 세트가 작다는 특징을 갖는다. 이 논문에서는 ECG 1D 신호를 2D 스펙트로그램 이미지로 변환하여 잡음의 영향을 최소화하고 전이학습과 메타학습의 장점을 결합하여 클래스 불균형 문제와 소수의 데이터에서도 빠른 학습이 가능하다는 특징을 갖는다. 따라서, 이 논문에서는 ECG 스펙트럼 이미지를 사용하여 2D-CNN 메타-전이 학습 기반 부정맥 분류 기법을 제안한다.

어텐션 기반 협업형 소스측 분산 서비스 거부 공격 탐지

김휘수 ( Hwisoo Kim ),정송헌 ( Songheon Jeong ),김경백 ( Kyungbaek Kim ) 한국정보처리학회 2024 정보처리학회 논문지 Vol.13 No.4

The evolution of the Distributed Denial of Service Attack(DDoS Attack) method has increased the difficulty in the detection process. One of the solutions to overcome the problems caused by the limitations of the existing victim-side detection method was the source-side detection technique. However, there was a problem of performance degradation due to network traffic irregularities. In order to solve this problem, research has been conducted to detect attacks using a collaborative network between several nodes based on artificial intelligence. Existing methods have shown limitations, especially in nonlinear traffic environments with high Burstness and jitter. To overcome this problem, this paper presents a collaborative source-side DDoS attack detection technique introduced with an attention mechanism. The proposed method aggregates detection results from multiple sources and assigns weights to each region, and through this, it is possible to effectively detect overall attacks and attacks in specific few areas. In particular, it shows a high detection rate with a low false positive of about 6% and a high detection rate of up to 4.3% in a nonlinear traffic dataset, and it can also confirm improvement in attack detection problems in a small number of regions compared to methods that showed limitations in the existing nonlinear traffic environment.