• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.05a
• /
• pp.455-458
• /
• 2013

본 논문에서 제안하는 파일 보안 기능은 암호알고리즘을 이용하여 윈도우 운영체제에서 파일을 안전하게 저장함으로써 허락되지 않은 사용자의 접근을 제한하도록 한다. 암호화하여 저장된 파일은 복호화 알고리즘으로 복호화해서 파일데이터를 읽게 된다. 이러한 기능은 사용자들이 편리하게 사용할 수 있도록 사용자 인터페이스를 설계하여 프로그램으로 구현한다. 보안 기능으로 구현된 파일 암호화 및 복호화 프로그램을 구동시키고 정상적으로 동작하는지의 여부를 실험하게 된다. 또한 복호화시 암호화 할 때의 설정과 설정이 틀 릴 경우 복호화가 되는지의 여부도 실험한다. 이러한 기능을 편리하게 사용할 수 있도록 Visual Studio 환경을 이용하여 UI(User Interface) 기능을 설계한다.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.11
• /
• pp.195-200
• /
• 2019

The purpose of this paper is to explore security guard's status and roles in society through media reports. Research method is to anlyze security Guard's 'Keyword Trend' and 'Keyword Frequency Analysis' by 'Big Kind' which enables 'News Big Data' analysis. The result came out by the analysis in sectional private security guard's history of settling down, growing up (quantity), and growing up (quality) by separating generations is that there are lots of attention and exposure from media about crime, security guard job, minimum wage, and 'Gabjil', but the images of security guard are recognized as victim of crime and 'Gabjil', and working in poor environment with minimum waged and ambiguous job, instead of people preventing crimes. In the future, stabilizing security guard's social status and work responsibility, and developing job professionalism are necessary to improve the images of security guard.

• Journal of Internet of Things and Convergence
• /
• v.9 no.2
• /
• pp.55-60
• /
• 2023

Recently, demand for cloud computing has increased and remote access due to home work and external work has increased. In addition, a new security paradigm is required in the current situation where the need to be vigilant against not only external attacker access but also internal access such as internal employee access to work increases and various attack techniques are sophisticated. As a result, the network security model applying Zero-Trust, which has the core principle of doubting everything and not trusting it, began to attract attention in the security industry. Zero Trust Security monitors all networks, requires authentication in order to be granted access, and increases security by granting minimum access rights to access requesters. In this paper, we explain zero trust and zero trust architecture, and propose a new cloud security system for strengthening access control that overcomes the limitations of existing security systems using zero trust and blockchain and can be used by various companies.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.67 no.2
• /
• pp.90-93
• /
• 2018

This paper is a system that visually informs the hearing impaired to visit other people by blinking the light of a room using the IoT(Internet of Things) technology. The system combines the power of home-use lights with low-power IoT devices to provide visual notifications. Using a current sensor, this system can track user location and then turns on and off the light in that room only to save energy. The proposed idea can create a society that is equal to everyone and can live more conveniently.

• International Journal of Computer Science & Network Security
• /
• v.21 no.8
• /
• pp.369-376
• /
• 2021

One of the most active areas of research in the field of affective computing and signal processing is emotion recognition. This paper proposes emotion recognition of low-resource (Sindhi) language. This work's uniqueness is that it examines the emotions of languages for which there is currently no publicly accessible dataset. The proposed effort has provided a dataset named MAVDESS (Mehran Audio-Visual Dataset Mehran Audio-Visual Database of Emotional Speech in Sindhi) for the academic community of a significant Sindhi language that is mainly spoken in Pakistan; however, no generic data for such languages is accessible in machine learning except few. Furthermore, the analysis of various emotions of Sindhi language in MAVDESS has been carried out to annotate the emotions using line features such as pitch, volume, and base, as well as toolkits such as OpenSmile, Scikit-Learn, and some important classification schemes such as LR, SVC, DT, and KNN, which will be further classified and computed to the machine via Python language for training a machine. Meanwhile, the dataset can be accessed in future via https://doi.org/10.5281/zenodo.5213073.

• International Journal of Computer Science & Network Security
• /
• v.21 no.8
• /
• pp.87-96
• /
• 2021

The demand for e-learning through video lectures is rapidly increasing due to its diverse advantages over the traditional learning methods. This led to massive volumes of web-based lecture videos. Indexing and retrieval of a lecture video or a lecture video topic has thus proved to be an exceptionally challenging problem. Many techniques listed by literature were either visual or audio based, but not both. Since the effects of both the visual and audio components are equally important for the content-based indexing and retrieval, the current work is focused on both these components. A framework for automatic topic-based indexing and search depending on the innate content of the lecture videos is presented. The text from the slides is extracted using the proposed Merged Bounding Box (MBB) text detector. The audio component text extraction is done using Google Speech Recognition (GSR) technology. This hybrid approach generates the indexing keywords from the merged transcripts of both the video and audio component extractors. The search within the indexed documents is optimized based on the Naïve Bayes (NB) Classification and K-Means Clustering models. This optimized search retrieves results by searching only the relevant document cluster in the predefined categories and not the whole lecture video corpus. The work is carried out on the dataset generated by assigning categories to the lecture video transcripts gathered from e-learning portals. The performance of search is assessed based on the accuracy and time taken. Further the improved accuracy of the proposed indexing technique is compared with the accepted chain indexing technique.

• International Journal of Computer Science & Network Security
• /
• v.23 no.7
• /
• pp.39-48
• /
• 2023

Breast cancer screening makes extensive utilization of mammography. Even so, there has been a lot of debate with regards to this application's starting age as well as screening interval. The deep learning technique of transfer learning is employed for transferring the knowledge learnt from the source tasks to the target tasks. For the resolution of real-world problems, deep neural networks have demonstrated superior performance in comparison with the standard machine learning algorithms. The architecture of the deep neural networks has to be defined by taking into account the problem domain knowledge. Normally, this technique will consume a lot of time as well as computational resources. This work evaluated the efficacy of the deep learning neural network like Visual Geometry Group Network (VGG Net) Residual Network (Res Net), as well as inception network for classifying the mammograms. This work proposed optimization of ResNet with Teaching Learning Based Optimization (TLBO) algorithm's in order to predict breast cancers by means of mammogram images. The proposed TLBO-ResNet, an optimized ResNet with faster convergence ability when compared with other evolutionary methods for mammogram classification.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.21 no.4
• /
• pp.115-124
• /
• 2011

There has been significant research in security technology such as e-passport standards, as e-passports have been introduced internationally. E-passports combine the latest security technologies such as smart card, public key infrastructure, and biometric recognition, so that these technologies can prevent unauthorized copies and counterfeits. Biometric information stored in e-passports is the most sensitive personal information, and it is expected to bring the highest risk of damages in case of its forgery or duplication. The present e-passport standards cannot handle security features that verify whether its biometric information is copied or not. In this paper, we propose an e-passport security technology in which biometric watermarking is used to prevent the copy of biometric information in the e-passport. The proposed method, biometric watermarking, embeds the invisible date of acquisition into the original data during the e-passport issuing process so that the human visual system cannot perceive its invisibly watermarked information. Then the biometric sample, having its unauthorized copy, is retrieved at the moment of reading the e-passport from the issuing database. The previous e-passport security technology placed an emphasis on both access control readers and anti-cloning chip features, and it is expected that the proposed feature, copy protection of biometric information, will be demanded as the cases of biometric recognition to verify personal identity information has increased.

• Korean Journal of Optics and Photonics
• /
• v.14 no.6
• /
• pp.630-635
• /
• 2003

We propose an encryption method using visual cryptography and virtual phase images. In the encryption process, the original image is shared by virtual images and the decryption key image. We multiply the virtual phase images with each complex image, which has the constant value of its sum after performing the phase modulation of the virtual images and the decryption key. The encryption cards are made by Fourier transforming the multiplied images. It is possible to protect information about the original image because the cards do not have any information from the original image. To reconstruct the original image, all the encryption cards are placed on each path of a Mach-Zehnder interferometer and then the lights passing through them are summed. Since the summed image is inverse Fourier transformed by a Fourier lens, the phase image is multiplied with the decryption key and the output image is obtained in the form of intensity on the CCD plane. Computer simulations show a good performance of the pro-posed optical security system.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.5
• /
• pp.975-986
• /
• 2022

Deep learning is attracting great attention, showing excellent performance in image processing, but is vulnerable to adversarial attacks that cause the model to misclassify through perturbation on input data. Adversarial examples generated by adversarial attacks are minimally perturbated where it is difficult to identify, so visual features of the images are not generally changed. Unlikely deep learning models, people are not fooled by adversarial examples, because they classify the images based on such visual features of images. This paper proposes adversarial attack detection method using Symbolic Representation, which is a visual and symbolic features such as color, shape of the image. We detect a adversarial examples by comparing the converted Symbolic Representation from the classification results for the input image and Symbolic Representation extracted from the input images. As a result of measuring performance on adversarial examples by various attack method, detection rates differed depending on attack targets and methods, but was up to 99.02% for specific target attack.