• 사물인터넷융복합논문지
• /
• 제5권1호
• /
• pp.7-11
• /
• 2019

본 연구는 최근 전국적으로 계속해서 사물인터넷 CCTV의 설치 대수가 증가함에 따라 CCTV의 활용범위를 넓히고자 CCTV를 통하여 범죄 의심자 또는 이상 행동자를 추적하는 방법을 제안한다. 이상 행동 구분은 기존에 나와 있던 연구들을 활용하여 범죄 의심자 또는 이상 행동자를 색출해내고 CNN을 활용하여 대상을 객체와 하여 추적을 하고 주변 CCTV를 서로 네트워크로 연결하여 객체화된 대상의 이동 경로를 예측해 해당 경로 근방의 CCTV들에 객체의 샘플 데이터를 공유하여 대상 판별 및 해당 대상을 추적하는 방식을 이용하였다. 해당 연구를 통하여 추적하기 힘든 범죄자의 위치를 추적하여 국가 치안에 기여하고 더욱 다양한 기술들이 CCTV에 접목될 수 있도록 지속적인 연구가 필요하다.

• 한국산업정보학회논문지
• /
• 제15권3호
• /
• pp.41-49
• /
• 2010

최근 RFID 시스템은 응용 범위를 넓혀가고 있으나 무선 통신의 불안전한 특성으로 인한 정보 보안 문제 및 응용 객체별 별도 태그 사용에 의한 불편함 등의 문제점들을 내포하고 있다. 따라서 RFID 기술을 응용한 시스템의 확산을 위해서는 안정적인 정보 보호를 바탕으로 한 여러 응용 객체들 간의 효율적인 정보 공유에 대한 연구가 마련되어야 한다. 본 논문에서는 하나의 태그로 다수 개의 RFID 응용 객체들에 접근할 수 있도록 하는 다중 객체 접근을 위한 RFID 태그 구조를 설계하고, 이러한 태그 내에 저장되는 각 응용 객체에 대한 정보를 보호하기 위한 암호화 알고리즘을 제안한다. 제안하는 알고리즘은 기존의 암호화 기법인 SEED 알고리즘을 RFID 시스템의 특성에 맞도록 경량화한 방법이다. 태그 정보를 보호하기 위한 SEED 변형 알고리즘의 성능은 암 복호화의 속도를 측정하여 기존의 SEED 알고리즘과 비교하여 평가한다.

• 융합보안논문지
• /
• 제22권5호
• /
• pp.11-20
• /
• 2022

인터넷과 웹 기술이 모바일 장치 중심으로 발전하면서 이미지 데이터는 사람, 텍스트, 공간 등 다양한 유형의 민감정보를 담고 있다. 이러한 특성과 더불어 SNS 사용이 증가하면서 온라인 상의 개인정보가 노출되고 악용되는 피해 규모가 커지고 있다. 그러나 개인정보보호를 위한 다중 유형 객체 탐지 기반의 비식별화 기술에 관한 연구는 미흡한 상황이다. 이에 본 논문은 기존의 단일 유형 객체 탐지 모델을 병렬적으로 이용하여 다중 유형의 객체를 탐지 및 비식별화하는 인공지능 모델을 제안한다. Cutmix 기법을 통해 사람과 텍스트 객체가 함께 존재하는 이미지를 생성하여 학습 데이터로 구성하고, 사람과 텍스트라는 다른 특징을 가진 객체에 대한 탐지 및 비식별화를 수행하였다. 제안하는 모델은 두 가지 객체가 동시에 존재할 때 0.724의 precision과 0.745의 mAP@.5 를 달성한다. 또한, 비식별화 수행 후 전체 객체에 대해 mAP@.5 가 0.224로, 0.4 이상의 감소폭을 보였다.

• 디지털산업정보학회논문지
• /
• 제13권1호
• /
• pp.49-57
• /
• 2017

IoT can be connected through a single network not only objects which can be connected to existing internet but also objects which has communication capability. This IoT environment will be a huge change to the existing communication paradigm. However, the big security problem must be solved in order to develop further IoT. Security mechanisms reflecting these characteristics should be applied because devices participating in the IoT have low processing ability and low power. In addition, devices which perform abnormal behaviors between objects should be also detected. Therefore, in this paper, we proposed D-IDS technique for efficient detection of malicious attack nodes between devices participating in the IoT. The proposed technique performs the central detection and distribution detection to improve the performance of attack detection. The central detection monitors the entire network traffic at the boundary router using SVM technique and detects abnormal behavior. And the distribution detection combines RSSI value and reliability of node and detects Sybil attack node. The performance of attack detection against malicious nodes is improved through the attack detection process. The superiority of the proposed technique can be verified by experiments.

• International Journal of Computer Science & Network Security
• /
• 제24권6호
• /
• pp.99-108
• /
• 2024

The Internet of Things (IoT) is a novel concept that allows a large number of objects to be connected to the Internet while also allowing them to be controlled remotely. The Internet of Things is extensive and has become an almost inseparable part of our daily lives. Users' personal data is frequently obtained by these linked gadgets and stored online. In recent years, the security of acquired data has become a major concern. As devices grow more linked, privacy and security concerns grow more pressing, and they must be addressed as soon as possible. IoT implementations and devices are particularly vulnerable to attacks that might adversely affect customer security and privacy, which might have an impact on their practical utility. The goal of this study is to bring attention to the security and privacy concerns that exist in IoT systems. To that purpose, the paper examines security challenges at each level of the IoT protocol stack, identifies underlying impediments and critical security requirements, and provides a rapid overview of available security solutions for securing IoT in a layered environment.

• 한국멀티미디어학회논문지
• /
• 제20권8호
• /
• pp.1312-1320
• /
• 2017

Recently, vector map data is developed and used in many domains widely. In the most cases, vector map data contains confidential information which must be kept away from unauthorized users. Moreover, the production process of vector maps is considerably complex and consumes a lot of money and human resources. Therefore, the secured storage and transmission are necessary to prevent the illegal copying and distribution from hacker. This paper presents a selective encryption algorithm using geometric objects in frequency domain for vector map data. In the proposed algorithm, polyline and polygon data in vector map is the target of the selective encryption process. Experimental results verified that proposed algorithm is effectively and adaptive the requirements of security.

• 한국재난정보학회 논문집
• /
• 제6권2호
• /
• pp.11-20
• /
• 2010

All of the people or objects which are contacted during the activity of guard are added to range of objects. guard has to notice decision, question proposal, observation, accomplish to be happened them at the same time recognizing the steps as soon as possible. Before a lot of information of client are shown, guard expert has to search observation of materialization, extension of reservation, notification of business and causes of danger through personal interviews. Rapid communication system has to be assumed and effective caution, protection and shelter and following prevention are cooperated as well as has to care about safe of guard object by a protective wall. And also has to get out of the ground, keep the large shape when moves, prevent the trials of attack from the assassinators after takeing control over weapons.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -3
• /
• pp.1416-1419
• /
• 2002

This paper describes an implementation method for the people counting system which detects and tracks moving people using a fixed single camera. This system counts the number of moving objects (people) entering the security door. Moreover, the detected objects are tracked by the proposed tracking algorithm before entering the door. The proposed system with In-tel Pentium IV operates at an average rate of 10 frames a second on real world scenes where up to 6 persons come into the view of a vertically mounted camera.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2006년도 하계종합학술대회
• /
• pp.297-298
• /
• 2006

In this paper, we propose a real-time surveillance system for security of important area such as military bases, prisons, and strategic infra structures. The proposed system recognizes the movement of objects in dark environments. First, the Multi-scale retinex (MSR) is processed to enhance the contrast of image captured in dark environments. Then, the enhanced input image is subtracted with the background image. Finally, each bounding box enclosing each objects are tracked. The center point of each bounding box obtained by the proposed algorithm provides more accurate tracking information. Experimental results show that the proposed system provides good performance even though an object moves very fast and the background is quite dark.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2006년도 하계종합학술대회
• /
• pp.831-832
• /
• 2006

In this paper, we introduce a canonical framework of the large-scaled web-based sensor gateway and practically implement it as the environment monitoring system. The system consists of a central management server, up to 250 local embedded subsystems and up to 250 sensor or actuator nodes for each subsystem. The node information is gathered periodically through a well-defined protocol on the sensor network and converted to the web contents and the SNMP MIB objects according to its data type. The MIB objects are well-defined and include system, network, sensor, actuator and alarm specific data classes. Because there is an increasing trend that a large number of sites are willing to adapt unmanned sensing and control, the developed system will play a key role to efficiently manage a large scale sensor networked system such as environment monitoring systems or countermeasure systems against disaster and calamities.