• Review of KIISC
• /
• v.32 no.4
• /
• pp.7-17
• /
• 2022

운전자 보조 시스템을 통한 차량의 전자적인 제어를 위하여, 최근 차량에 탑재된 전자 제어 장치 (ECU; Electronic Control Unit)의 개수가 급증하고 있다. ECU는 효율적인 통신을 위해서 차량용 내부 네트워크인 CAN(Controller Area Network)을 이용한다. 하지만 CAN은 기밀성, 무결성, 접근 제어, 인증과 같은 보안 메커니즘이 고려되지 않은 상태로 설계되었기 때문에, 공격자가 네트워크에 쉽게 접근하여 메시지를 도청하거나 주입할 수 있다. 악의적인 메시지 주입은 차량 운전자 및 동승자의 안전에 심각한 피해를 안길 수 있기에, 최근에는 주입된 메시지를 식별하기 위한 침입 탐지 시스템(IDS; Intrusion Detection System)에 대한 연구가 발전해왔다. 특히 최근에는 AI(Artificial Intelligence) 기술을 이용한 IDS가 다수 제안되었다. 그러나 제안되는 기법들은 특정 공격 데이터셋에 한하여 평가되며, 각 기법에 대한 탐지 성능이 공정하게 평가되었는지를 확인하기 위한 평가 프레임워크가 부족한 상황이다. 따라서 본 논문에서는 machine learning/deep learning에 기반하여 제안된 차랑용 IDS 5가지를 선정하고, 기존에 공개된 데이터셋을 이용하여 제안된 기법들에 대한 비교 및 평가를 진행한다. 공격 데이터셋에는 CAN의 대표적인 4가지 공격 유형이 포함되어 있으며, 추가적으로 본 논문에서는 메시지 주기 유형을 활용한 공격 유형을 제안하고 해당 공격에 대한 탐지 성능을 평가한다.

• Annual Conference of KIPS
• /
• 2011.11a
• /
• pp.219-222
• /
• 2011

본 논문에서는 스팸 SMS 발신번호와 메시지 텍스트의 특징을 기계학습한 스팸 필터링 시스템을 논한다. 최근 변화하는 스팸SMS에 대한 적응력을 위해서, 각 트레이닝 셋의 수신 텍스트를 음절단위로 분석 할 것을 제안한다. 그리고 기존의 분류기는 성능이 미흡하거나 구현의 복잡성으로 인해 실제로 스펨 필터엔진으로 활용되지 않는 점을 극복하기 위해서 보다 단순한 분류기를 사용한다. 제안하는 시스템은 트레이닝 셋의 발신번호 및 수신 텍스트의 음절단위를 빈도수와 묶어 학습데이터를 구성하고, 테스트 셋을 스팸적 논스팸적으로 분석하여 스팸일 확률을 계산한다. 또한 Naive baysian를 바탕으로 한 경계값 기반 분류기를 통해, 타 분류기에 비해 구현 및 활용면에서 실용성이 높으면서도 성능이 뒤처지지 않는 시스템을 제안한다.

• Annual Conference of KIPS
• /
• 2008.11a
• /
• pp.936-939
• /
• 2008

차량 내부 네트워크(In-Vehicle Network)에 많은 관심이 고조되는 가운데 Time-Triggered 와 Event-Triggered 패러다임의 장점을 모두 갖춘 하이브리드(Hybrid) 프로토콜인 FlexRay 가 최근 들어 많은 자동차 분야 업체들로부터 주목 받으면서 이에 대한 다양한 성능 분석 시도가 이루어지고 있다. 하지만 FlexRay 프로토콜의 메시지 전송의 유연성(Flexibility)으로 인해 정확한 성능 분석에 많은 어려움이 있다. 이에 본 논문에서는 다양한 길이의 메시지를 고려한 동적 구간 분석 모델을 제안하였고, 이를 바탕으로 잔여 미니 슬롯 확률 분포(Empty Minislot Distribution)를 도출하였으며 FlexRay 메시지 셋(Set)를 이용한 실험을 통하여 특정 길이의 동적 구간에서 미니 슬롯 개수에 따른 잔여 미니 슬롯 발생확률 값의 변화를 확인하였다.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.24 no.4
• /
• pp.75-90
• /
• 2013

Given the context that users are actively using social media with multimedia embedded information, the purpose of this study is to demonstrate how images are used within Twitter messages, especially in influential and favorited messages. In order to achieve the purpose of this study, the top 200 influential and favorited messages with images were selected out of 1,589 tweets related to "Boston bombing" in April 2013. The characteristics of the message, image use, and user are analyzed and compared. Two phases of the analysis were conducted on three data sets containing the top 200 influential messages, top 200 favorited messages, and general messages. In the first phase, coding schemes have been developed for conducting three categorical analyses: (1) categorization of tweets, (2) categorization of image use, and (3) categorization of users. The three data sets were then coded using the coding schemes. In the second phase, comparison analyses were conducted among influential, favorited, and general tweets in terms of tweet type, image use, and user. While messages expressing opinion were found to be most favorited, the messages that shared information were recognized as most influential to users. On the other hand, as only four image uses - information dissemination, illustration, emotive/persuasive, and information processing - were found in this data set, the primary image use is likely to be data-driven rather than object-driven. From the perspective of users, the user types such as government, celebrity, and photo-sharing sites were found to be favorited and influential. An improved understanding of how users' image needs, in the context of social media, contribute to the body of knowledge of image needs. This study will also provide valuable insight into practical designs and implications of image retrieval systems or services.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.6
• /
• pp.284-298
• /
• 2022

It is necessary to acquire information on traffic safety facilities installed on the roadways specifically for the operation of autonomous vehicles. The purpose of this study is to prepare a Korean version of an integrated message-set design as a way to provide to autonomous vehicles standardized information on traffic safety facilities. In this study, necessary facilities are classified according to four criteria (no legal basis; not providing information to autonomous vehicles; providing duplicate information; not standardized, and too difficult to generalize) based on information that must be provided to operate autonomous vehicles. The priority of information delivery (gross negligence followed by behavior change) was classified according to the importance of the information to be provided during autonomous driving, and the form was defined for the classification code in the information delivered. Finally, the information location and delivery method of traffic facilities for compliance with SAE J2735 were identified. This study is meaningful in that it provides a plan for roadway operations by suggesting a method for providing information to autonomously driven vehicles.

• Annual Conference of KIPS
• /
• 2022.05a
• /
• pp.157-160
• /
• 2022

딥러닝이 각광받기 시작하면서 인간의 자세와 행동을 인식하고 분류하기 위한 인공지능 기술 또한 급속도로 발전하게 되었다. 영상에서 인간의 자세를 디지털 데이터로 표현할 때 인체의 주요 관절점의 위치와 연결관계를 나타내는 스켈레톤 표현 방식을 주로 사용한다. 본 논문에서는 스켈레톤 데이터에 비밀 메시지를 은닉할 수 있는 스테가노그라피 알고리즘에 대해 소개하고, 스켈레톤을 구성하는 주요 관절점 키포인트를 조작했을 때 행동 인식 인공지능 모델이 어떻게 반응하는지 살펴봄으로써 스켈레톤 데이터에 대한 스테가노그라피 알고리즘의 특성과 보안성에 대해 논의한다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.4
• /
• pp.681-691
• /
• 2024

In recent decades, research and development in the field of industrial robotics, such as an unmanned ground vehicle (UGV) and an unmanned aerial vehicle (UAV), has been significant progress. In these advancements, it is important to use middleware, which facilitates communication and data management between different applications, and various industrial communication middleware protocols have been released. The robot operating system (ROS) is the most widely adopted as the main platform for robot system development among the communication middleware protocols. However, the ROS is known to be vulnerable to various cyber attacks, such as eavesdropping on communications and injecting malicious messages, because it was initially designed without security considerations. In response, numerous studies have proposed countermeasures to ROS vulnerabilities. In particular, some work has been proposed on generating ROS datasets for intrusion detection systems (IDS), but there is a lack of research in this area. In this paper, in order to contribute to improving the performance of ROS IDSs, we propose a new type of attack scenario that can occur in the ROS and build ROS attack datasets collected from a real robot system and make it available as an open dataset.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.1C
• /
• pp.25-34
• /
• 2004

In mobile agent environments, cascaded delegations among places occur frequently due to the mobility of agents. Cascaded delegation in mobile agent environments can be defined as the process whereby the delegated place delegates the rights of the delegating place further. The representative study for delegation in mobile agent environments is Berkovits et al.'s study. Their study only defines the messages that is sent between the place executing the agent and the place where the agent migrates. Because their study considers only the delegation between two places which participate in migration of an agent, it is inadequate in the situation that the cascaded delegation is necessary. In other words, the relationships among the messages sent from and to places is necessary. However, their study does not exist the relationships. In this paper, we propose a delegation scheme that provides agents with secure cascaded delegation. The proposed scheme achieves the goal by nesting each delegation token within the signed part of the next immediate delegation token. We prove that the proposed scheme is secure against the attack of replaying a message and of substituting a delegation token.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.11 no.1
• /
• pp.72-85
• /
• 2012

Today, although most bluetooth hands-free devices within a vehicle provide telephone service functions such as voice communication, caller id display and SMS message display and so on, they do not provide a function that displays Internet-based text data. We need to develop a scheme that displays the internet-based text data including existing hands-free function because the request for using the Internet service is increasing within a vehicle recently. The proposed bluetooth device application includes advanced function such as SNS message arrival notification, the message display function and we chose Android as the implementation mobile platform giving consideration to the fact that most SNS applications operate on Android and the platform is easily embedded into small embedded device. Smartphone or tablet PC connected with the proposed bluetooth device is an Android-based device and we designed a form of Android app for the function implementation of the devices. When the audio-text gateway app receives SNS text data, it extracts title and sender information from the message header information in a form of text data and sends them via ACL (Asynchronous Connection-Oriented) link to the bluetooth device showing the data on the screen. Android-based bluetooth devices are not possible to play voice through speaker because the bluetooth hands-free or headset profile ported within Android platform normally only includes audio gateway's function. The proposed bluetooth device application, therefore, applies the streaming scheme that sends data via ACL link instead of the way that sending them via SCO (Synchronous Connection-Oriented) link.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.26 no.3
• /
• pp.693-700
• /
• 2016

Analyzing characteristics of spam text messages had limitations since spam datasets are typically difficult to obtain publicly and previous studies focused on spam email. Although existing studies, such as through the use of spam e-mail characterization and utilization of data mining techniques, there are limitations that influence is limited to high spam detection techniques using a single word character. In this paper, we reveal the characteristics of the spam SMS based on experiment and analysis from different perspectives and propose coward analysis based spam SMS detection scheme with a publicly disclosed spam SMS from the University of Singapore. With the extensive performance evaluations, we show false positive and false negative of the proposed method is less than 2%.