• Journal of Information Processing Systems
• /
• v.20 no.3
• /
• pp.375-390
• /
• 2024

Edge computing architecture has effectively alleviated the computing pressure on cloud platforms, reduced network bandwidth consumption, and improved the quality of service for user experience; however, it has also introduced new security issues. Existing anomaly detection methods in big data scenarios with cloud-edge computing collaboration face several challenges, such as sample imbalance, difficulty in dealing with complex network traffic attacks, and difficulty in effectively training large-scale data or overly complex deep-learning network models. A lightweight deep-learning model was proposed to address these challenges. First, normalization on the user side was used to preprocess the traffic data. On the edge side, a trained Wasserstein generative adversarial network (WGAN) was used to supplement the data samples, which effectively alleviates the imbalance issue of a few types of samples while occupying a small amount of edge-computing resources. Finally, a trained lightweight deep learning network model is deployed on the edge side, and the preprocessed and expanded local data are used to fine-tune the trained model. This ensures that the data of each edge node are more consistent with the local characteristics, effectively improving the system's detection ability. In the designed lightweight deep learning network model, two sets of convolutional pooling layers of convolutional neural networks (CNN) were used to extract spatial features. The bidirectional long short-term memory network (BiLSTM) was used to collect time sequence features, and the weight of traffic features was adjusted through the attention mechanism, improving the model's ability to identify abnormal traffic features. The proposed model was experimentally demonstrated using the NSL-KDD, UNSW-NB15, and CIC-ISD2018 datasets. The accuracies of the proposed model on the three datasets were as high as 0.974, 0.925, and 0.953, respectively, showing superior accuracy to other comparative models. The proposed lightweight deep learning network model has good application prospects for anomaly traffic detection in cloud-edge collaborative computing architectures.

• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.1
• /
• pp.71-75
• /
• 2008

Many sensor operating systems have memory limitation constraint; therefore, stack memory areas of threads resides in a single memory space. Because most target platforms do not have hardware MMY (Memory Management Unit), it is difficult to protect each stack area. The method to solve this problem is to exchange original stack handling instructions in binary code for wrapper routines to protect stack area. In this exchanging phase, instruction corruption problem occurs due to difference of each instruction length between stack handling instructions and branch instructions. In this paper, we propose the algorithm to call a target routine without instruction corruption problem. This algorithm can reach a target routine by repeating branch instructions to have a short range. Our solution makes it easy to apply security patch and maintain upgrade of software of sensor node.

• Journal of the Korea Safety Management & Science
• /
• v.15 no.3
• /
• pp.37-50
• /
• 2013

It is not an exaggeration to say that modern chemicals take a leading place in our life, and people live with the chemicals, having a huge impact on their daily life. The chemical industry in South Korea, ranked seventh in the world, is one of the key industries that are forming greater part of Korean economy. The actual state of the chemical industries, however, is that over 14 tons of hazardous chemicals are being discharged annually and threaten people's lives with a lack of knowledge of its potential danger. In this way, not only beneficial to us, some of these substances, All chemicals, but also present a threat fundamentally our living environment to hazards to human health and the environment, accidents such chemicals, unlike accidents general understanding the scale of damage and propagation velocity has a complex very difficult risk profile, that can occur during deployment of an accident type is also very diverse. Is the actual situation of public concern against harmful chemicals management's is amplified by the chemical accident in the wake such accidents, government and corporate and reactive system and management system prior to the chemical accident the need for communication to exchange ideas with each other between residents, providing information is important. Therefore, the government departments and corporations, which manage variety of chemicals, ought to contribute toward a development of national security by rigid control over the Hazardous chemicals.

• Journal of Korean Society of Archives and Records Management
• /
• v.1 no.2
• /
• pp.101-119
• /
• 2001

In this paper we explain the definition and component of electronic records, and reestablish the principle of the preservation. Also we discuss the conceptual approaches and requirements for long-term preservation in an electronic environment. The preservation in digital environment is to protect itself of record identity with the reliability and authenticity, and to ensure the accessibility of records. It needs to be periodical migration along with digital environment change for the long-term preservation of the electronic records. and to select software independent standard format. to ensure the integrity of electronic records along with this preservation strategy, process and relative information required for digital preservation are to record in the form of metadata. The preservation system is separated into four functional entities ; registration process, preservation process, access process, main record management system. Also, this article is conceptually to introduce the selection criteria of storage media, the security provision for the archive collections and the disaster recovery which apply to the digital archives.

• Korean Journal of Remote Sensing
• /
• v.33 no.5_2
• /
• pp.617-620
• /
• 2017

The periodic monitoring of crop conditions and timely estimation of crop yield are of great importance for supporting agricultural decision-makings, as well as for effectively coping with food security issues. Remote sensing has been regarded as one of effective tools for crop condition monitoring and crop type classification. Since 2010, RDA (Rural Development Administration) has been developing technology for monitoring on crop condition using remote sensing and model. These special papers address recent state-of-the-art of remote sensing and geospatial technologies for providing operational agricultural information, such as, crop yield estimation methods using remote sensing data and process-oriented model, crop classification algorithm, monitoring and prediction of weather and climate based on remote sensing data,system design and architecture of crop monitoring system, history on rice yield forecasting method.

• Journal of Cadastre & Land InformatiX
• /
• v.45 no.2
• /
• pp.87-100
• /
• 2015

Currently, Korea government has strongly recommended the storm and flood insurance system to reduce the damage caused by natural disasters. The storm and flood insurance operated by private insurance company is the type of policy insurance. and is supervised by Minister of Public Safety and Security. It is the advanced disaster management system which is able to protect the public interests through unexpected natural disaster by assisting some part of the insurance premium from a central or local government. The main purpose of the present investigation is to build the insurance object GIS DB which should be necessary to calculate the premium rate in the map for storm and flood insurance, and also, to perform GIS analysis. The service model in this study is aimed to general single house, apartment and green house. The service management plan targeting the whole country has been investigated in terms of building DB and service operation.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.3
• /
• pp.1350-1355
• /
• 2011

It is very important issues to protect many system resources using authorized client authentication in distributed client server systems. So it is not enough to prevent unauthorized opponents from attacking our systems that client authentication is performed using only the client's identifier and password. In this paper, we propose a secure authentication database modeling with two authentication keys such as a client authentication key and a server authentication key. The proposed authentication model can be used making high quality of computer security using two authentication keys during transaction processing. The two authentication keys are created by client and server, and are used in every request transaction without user's extra input. Using the proposed authentication keys, we can detect intrusion during authorized client's transaction processing because we can know intrusion immediately through comparing stored authentication keys in client server systems when hackers attack our network or computer systems.

• Journal of Advanced Navigation Technology
• /
• v.12 no.3
• /
• pp.245-254
• /
• 2008

If the broadcast message is sent, first of all, the privileged users will decode the session key by using his or her personal key, which the user got previously. The user willget the digital information through this session key. As shown above, the user will obtain messages or session keys using the keys transmitted from a broadcaster, which process requires effective ways for the broadcaster to generate and distribute keys. In addition, when a user wants to withdraw or sign up, an effective process to renew a key is required. It is also necessary to chase and check users' malicious activities or attacking others. This paper presents a method called Traitor Tracing to solve all these problems. Traitor tracing can check attackers and trace them. It also utilizes a proactive way for each user to have effective renewal cycle to generate keys.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.28 no.9
• /
• pp.99-104
• /
• 2014

This paper presents a unified live-streaming method based on Hypertext Mark-up Language 5(HTML5) for an IP camera which is independent of browsers of clients and is implemented with open-source libraries. Currently, conventional security systems based on analog CCTV cameras are being modified to newer surveillance systems utilizing IP cameras. These cameras offer remote surveillance and monitoring regardless of the device being used at any time, from any location. However, this approach needs live-streaming protocols to be implemented in order to verify real-time video streams and surveillance is possible after installation of separate plug-ins or special software. Recently, live streaming is being conducted through HTML5 using two different standard protocols: HLS and DASH, that works with Apple and Android products respectively. This paper proposes a live-streaming approach that is linked on either of the two protocols which makes the system independent with the browser or OS. The client is possible to monitor real-time video streams without the need of any additional plug-ins. Moreover, by implementing open source libraries, development costs and time were economized. We verified usefulness of the proposed approach through mobile devices and extendability to other various applications of the system.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.21 no.2
• /
• pp.164-170
• /
• 2015

This study proposes the improvement of maritime traffic management for domestic ships and fishing vessels by introducing the e-navigation environment. This study discusses the development of present Vessel Traffic service (VTS) in a systematic aspect and a fuctional aspect. The concept and architecture of e-navigation operation system based on the General Information Center on Maritime Safety and Security (GICOMS) are proposed as a solution for the improvement of maritime traffic management in Korean coastal waters. Especially, means of data exchange between ships and ship-shore based on the Maritime Cloud and regional e-Data Center are discussed. This study will help to the implementation of the Korean e-navigation project which focuses on the safety of small ships and fishing vessels. In the future, it is needed to study for the development and operation of accident prevention system under the e-navigation environment.