• Proceedings of the Korea Contents Association Conference
• /
• 2018.05a
• /
• pp.535-536
• /
• 2018

이 논문에서는 스마트 블랙박스를 위한 분산 이동객체 모니터링 시스템을 개발한다. 개발하는 모니터링 시스템은 대용량의 스마트 블랙박스의 데이터를 수집, 분석, 제공하는 기능과 수집된 블랙박스 데이터를 분석하여 안전 및 경제 운행 정보를 제공한다. 또한 차량의 위치를 기반으로 현재 위치 모니터링 및 차량 궤적 조회가 가능하다.

• Review of KIISC
• /
• v.24 no.2
• /
• pp.35-41
• /
• 2014

자동차 산업 인프라의 발달로 자동차 사용 인구는 지속적으로 증가하고 있으며, 이에 따른 자동차 사고도 매년 증가하고 있다. 자동차 사고는 개인 및 사회의 비용손실과 즉결되므로 많은 운전자들이 자동차용 블랙박스(사고영상기록장치)를 구입하여 장착하고 있다. 이런 자동차용 블랙박스는 교통사고 시점의 영상을 저장 재생 하므로 정확한 사고원인을 규명하는데 활용되고 교통사고를 예방하는 효과가 있다. 그러나 그 이면에 자동차용 블랙박스는 자동차가 운행될 때 마다 영상을 촬영하고 저장되기 때문에 의도되지 않은 개인의 사생활이 노출 될 수 있으며 또한 저장된 사고영상 데이터를 의도적으로 조작하여 교통사고의 원인규명을 방해하는 문제가 발생 하기도 한다. 본 연구에서는 이러한 문제를 해결하기 위한 국내 관련 동향을 알아보고 보안기술을 적용 할 수 있는 방안을 제시하고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.04a
• /
• pp.218-220
• /
• 2015

블랙박스는 많은 운전자들이 사고 발생 시 사고 경위를 파악하는데 널리 쓰이고 있다. 하지만 블랙박스의 시야각과 용량의 한계로 인해 사고 경위 파악에 어려움을 겪는다. 본 논문에서는 이런 문제를 해결하기 위해 차량 간 블랙박스 영상을 공유하는 시스템을 소개하고자 한다. 이 시스템을 통해 사고 차량은 다각도에서의 사고 영상을 얻을 수 있어 사고 경위 분석에 도움이 된다. 또한 이 시스템을 확장하여 차량뿐만 아니라 주변 영상 촬영기기 (CCTV 등)와도 영상을 공유할 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.605-608
• /
• 2009

최근 철도의 고속화, 자동화됨에 따라 철도 사고 역시 항공기 사고처럼 대형화 되고 인명피해 역시 매우 커지고 있다. 따라서 사고 발생시 사고원인을 신속하고 정확하게 분석하기 위해 철도 차량에 블랙박스의 설치를 법제화 하고 있고, 이에 대한 연구를 진행하고 있다. 사고의 정확한 판단을 위해서 블랙박스에 기록된 데이터를 분석하하는 분석 소프트웨어를 개발하였다. 본 논문의 블랙박스 분석 소프트웨어는 신속하고 정확하게 사고 원인을 규명할 수 있고, 구간별 운행 패턴과 기관사의 습관등을 파악할 수 있어, 운행을 개선 할 수 있어 사고를 미연에 방지 할 것으로 기대한다.

• Journal of KIISE
• /
• v.41 no.11
• /
• pp.982-991
• /
• 2014

The integrity assurance of recorded video by car black boxes are necessary as the car black box is becoming more popular. In this paper, we propose a video data integrity assurance scheme reflecting the features of car black box. The proposed method can detect any kind of deletion, insertion, modification of frames by cyclic chaining using inter block relation. And, it provides the integrity assurance function consistently even in cases of file overwriting because of no more free space in storage, partial file data lost. And non-repudiation is supported. Experimental results with a car black box embedded system with A8 application processor show that our method has a feasible computational overhead to process full HD resolution video at 30 frames per second in a real time.

• KIPS Transactions on Computer and Communication Systems
• /
• v.3 no.10
• /
• pp.351-356
• /
• 2014

Recently, automobile black boxes have evolved to support functionality to transfer videos stored in them into mobile phones via wireless network, from which the videos can be utilized for various purposes. This paper presents a method for automation of traffic violation reports using the automobile black boxes. When a traffic violation is captured by a black box, the proposed method helps a user to transfer the video capturing it into a mobile phone through a simple UI operation. With the video, an HTTP request to report the violation is automatically generated from the mobile phone, and then is transferred to a cyber-report center. We present a prototype system that implements the proposed method, and discuss several issues necessary to apply the method to real-world applications.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.19 no.6
• /
• pp.49-61
• /
• 2009

Recently, a great attention has been paid to a vehicle black box device in the auto markets since it provides an accident re-construction based on the data which contains audio, video, and some meaningful driving informations. It is expected that the device will get to promote around commercial vehicles and the market will greatly grow within a few years. Drivers who equips the device in their car believes that it can find the origin of an accident and help an objective judge. Unfortunately, the current one does not provide the integrity of the data stored in the device. That is the data can be forged or modified by outsider or insider adversary because it is just designed to keep the latest data produced by itself. This fact cause a great concern in car insurance and law enforcement, since the unprotected data cannot be trusted. To resolve the problem, in this paper, we propose a novel real-time integrity protection scheme for vehicle black box device. We also present the evaluation results by simulation using our software implementation.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.5
• /
• pp.817-826
• /
• 2022

AI technology is being successfully introduced in many fields, and models deployed as a service are deployed with black box environment that does not expose the model's information to protect intellectual property rights and data. In a black box environment, attackers try to steal data or parameters used during training by using model output. This paper proposes a method of inferring the type of model to directly find out the composition of layer of the target model, based on the fact that there is no attack to infer the information about the type of model from the deep learning model. With ResNet, VGGNet, AlexNet, and simple convolutional neural network models trained with MNIST datasets, we show that the types of models can be inferred using the output values in the gray box and black box environments of the each model. In addition, we inferred the type of model with approximately 83% accuracy in the black box environment if we train the big and small relationship feature that proposed in this paper together, the results show that the model type can be infrerred even in situations where only partial information is given to attackers, not raw probability vectors.

• Journal of KIISE
• /
• v.41 no.12
• /
• pp.1013-1017
• /
• 2014

A variety of applications that are accessible through app markets provide useful features and functions. However, those applications can present many GUI bugs due to the deficiency of testing processes. Even though various approaches have been developed for mobile app testing, GUI bugs in applications are still difficult to be identified due to the absence of efficiency, lack of automation, and necessity of access to the source code. In this paper, we propose an automated black-box testing method for efficient GUI bug detection. Our experimental results show that the proposed method achieves better code coverage and uncovers GUI bugs when compared with existing black-box testing called Monkey.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.290-293
• /
• 2013

Due to vehicle personal injury accident does not, and to analyze the cause and prevention of a variety of devices and technologies are coming out. Among other things, representative of the black box, and rear camera. Despite these advances in technology, and vehicle human injuries continue to occur. The reason for this is that the children, the negligence of the driver or the vehicle is in reverse when a person suddenly passed the back of the vehicle, or the rear of the existing detection system is properly detected was unable to. Therefore, In this paper, we want to design a black box to reveal the cause of the accident, using Kinect to prevent accidents, rear-view camera and rear integrated black box system.