• Convergence Security Journal
• /
• v.22 no.2
• /
• pp.9-19
• /
• 2022

As the expansion of digital transformation, we are more exposed to the threat of cyber attacks, and many institution or company is operating a signature-based intrusion prevention system at the forefront of the network to prevent the inflow of attacks. However, in order to provide appropriate services to the related ICT system, strict blocking rules cannot be applied, causing many false events and lowering operational efficiency. Therefore, many research projects using artificial intelligence are being performed to improve attack detection accuracy. Most researches were performed using a specific research data set which cannot be seen in real network, so it was impossible to use in the actual system. In this paper, we propose a technique for classifying major attack keywords in the security event log collected from the actual system, assigning a weight to each key keyword, and then performing a similarity check using TF-IDF to determine whether an actual attack has occurred.

• The Journal of Bigdata
• /
• v.7 no.2
• /
• pp.91-102
• /
• 2022

As artificial intelligence develops, AI chatbot systems are actively taking place. For example, in public institutions, the use of chatbots is expanding to work assistance and professional knowledge services in civil complaints and administration, and private companies are using chatbots for interactive customer response services. In this study, we propose a scenario-based AI voice chatbot system to reduce museum operating costs and provide interactive guidance services to visitors. The implemented voice chatbot system consists of a watcher object that detects the user's voice by monitoring a specific directory in real-time, and an event handler object that outputs AI's response voice by performing inference by model sequentially when a voice file is created. And Including a function to prevent duplication using thread and a deque, GPU operations are not duplicated during inference in a single GPU environment.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.1
• /
• pp.71-82
• /
• 2024

With the advancement of information and communication technology (ICT), the use of electronic document types such as PDF, MS Office, and HWP files has increased. Such trend has led the cyber attackers increasingly try to spread malicious documents through e-mails and messengers. To counter such attacks, AI-based methodologies have been actively employed in order to detect malicious document files. The main challenge in detecting malicious HWP(Hangul Word Processor) files is the lack of quality dataset due to its usage is limited in Korea, compared to PDF and MS-Office files that are highly being utilized worldwide. To address this limitation, data augmentation have been proposed to diversify training data by transforming existing dataset, but as the usefulness of the augmented data is not evaluated, augmented data could end up harming model's performance. In this paper, we propose an effective semi-supervised learning technique in detecting malicious HWP document files, which improves overall AI model performance via quantifying the utility of augmented data and filtering out useless training data.

• Journal of Platform Technology
• /
• v.12 no.2
• /
• pp.12-22
• /
• 2024

With the rapid increase in digital data in modern society, digital forensics plays a crucial role, and file type identification is one of its integral components. Research on the development of identification models utilizing artificial intelligence is underway to identify file types swiftly and accurately. However, existing studies do not support the identification of file types with high domestic usage rates, making them unsuitable for use within the country. Therefore, this paper proposes a more accurate file type identification model using Convolutional Neural Networks (CNN) and Gated Recurrent Units (GRU). To overcome limitations of existing methods, the proposed model demonstrates superior performance on the FFT-75 dataset, effectively identifying file types with high domestic usage rates such as HWP, ALZ, and EGG. The model's performance is validated by comparing it with three existing research models (CNN-CO, FiFTy, CNN-LSTM). Ultimately, the CNN and GRU based file type identification and classification model achieved 68.2% accuracy on 512-byte file fragments and 81.4% accuracy on 4096-byte file fragments.

• The Journal of Bigdata
• /
• v.9 no.1
• /
• pp.17-30
• /
• 2024

This study categorizes the factors that affect the intention to continue using ChatGPT into positive motivational factors (personalization, social influence) and negative motivational factors (privacy concern, perceived risk) and investigates whether they affect the intention to continue using ChatGPT through information trust, performance expectancy, and effort expectancy. To this end, a survey was conducted among 265 adults in their 20s and above who have used ChatGPT service. The results showed that personalization and social influence had a defining effect on information trust, performance expectancy, and effort expectancy. For privacy concern, we found a negative effect of wealth on performance expectations, but not on effort expectations. Perceived risk had a negative effect on performance expectancy and effort expectancy. In addition, information trust, performance expectancy, and effort expectancy have a defining effect on continuance intention. This study extends the scope of existing research that focuses on positive factors, deepens our the understanding of ChatGPT. It also provides useful suggestions for continued use of ChatGPT.

• Journal of the Institute of Convergence Signal Processing
• /
• v.25 no.1
• /
• pp.39-45
• /
• 2024

Recently, the paradigm of the aircraft industry, not only domestically but also globally, has been changing significantly starting with the era of the Fourth Industrial Revolution. With the convergence of new technologies such as ICT and AI, the drone market, centered around the military, is expanding its overall services to include the civilian market. Additionally, drones operate by being equipped with batteries, and for product lines that use batteries, lightening the product is one of the critical factors. This is because the lighter the aircraft, the less battery consumption and maximum efficiency. Therefore, recently, composite materials have been used to reduce the weight of the aircraft. To not only reduce weight but also achieve high functionality, it is being applied to most areas such as propellers, airframes, interior materials, floor plates, driving devices, and battery housings, and is emerging as a core technology. In this paper will utilize ceramic fiber composite materials, which have recently emerged for lightweight. It aims to improve noise and strength by targeting propellers, one of the most important factors in drones. In addition, the performance of the propeller developed through the low-noise design will be verified.

• Journal of Platform Technology
• /
• v.12 no.1
• /
• pp.141-150
• /
• 2024

The importance of personal data protection is increasingly emphasized both at home and abroad, and while overseas countries are applying various policies and dynamic management technologies, there are some gaps between compliance with laws and regulations and the application of technologies in Korea, and there are few user interfaces that provide convenient ways for data subjects to stop processing personal data. This study first analyzes the need for dynamic personal information consent management technology, the current state of the industry, and the prospects for its development. Next, this study proposes a basic model for dynamic management of personal information consent that maximizes the data subject's right to personal data self-determination while strictly complying with personal data protection laws in Republic of Korea. In particular, this study analyzes the basis of domestic laws and regulations related to the suspension of personal data processing, designs a basic model of personal data consent dynamic management interface, and presents its effectiveness. Based on the results of this study, we expect that the proposed dynamic management model for personal data use consent can be used in various ways for various websites and applications in the future.

• Journal of The Korean Association of Information Education
• /
• v.13 no.3
• /
• pp.371-382
• /
• 2009

The most widely-used typical information service of national education, EDUNET has members of 5.8million. But it has been not used in the fields of elementary school. There are short-comings in its usage by members of the elementary school teaching. We would like to find solutions by using a questionnaire to the teachers of elementary school in the Busan and Gyeongsangnam-do, which resolve the problems of the actual condition. Analytical results show that 93.1 percent of the teachers usually use private education information service and 5.3 percent use EDUNET service. The main reason why teachers discourage the use of EDUNET service is that it provides the inconvenience of searching data(29.4%) and insufficiency of good quality contents(25%). In order to revitalize using EDUNET service, EDUNET has to improve on the perceived cumbersome unhandy of searching tools and help teachers to use EDUNET service by offering information of high quality.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.23 no.2
• /
• pp.131-138
• /
• 2017

Lately, Internet-based vessels have begun to appear at sea with the development of ICT. Thereby crews have gained easy Internet access through increased smartphone portability. However, the side effects of smartphone use while on watch, have not been studied seriously despite being a reality. In this study, simulation experiments were carried out using a Ship Handling Simulator in order to distinguish the risks of using a smartphone while on watch. Proximity Evaluation, Control Evaluation, Subjective Evaluation and Situation Awareness to the dangerous situation were used to quantify risk during simulation, and analysis results were compared with cases when using and not using a smartphone. It was found that the degree of risk increased between 1.3 to 3 times given smartphone use. Consequently, this paper represents foundation for the restriction of smartphone use and proposes smartphone usage guideline for ship navigation.

• Journal of Korea Multimedia Society
• /
• v.19 no.2
• /
• pp.334-343
• /
• 2016

In this paper, we developed a low cost smart puck system that can interact with the intuitive operation of natural finger touches. The tangible smart puck, designed for capacitive tabletop display, has Arduino embedded processor which communicates only with the MT server. The MT server communicates both to the smart puck and the display server. The display server displays the relevance information on the location of the smart pucks on the tabletop display and handles interactions with the users. The experiment results show that the accuracy of identifying the smart puck ID was very reliable enough to use in practice, and the information presentation processing time is confirmed excellent enough compared to traditional expensive commercial products.