• Journal of Internet Computing and Services
• /
• v.23 no.6
• /
• pp.39-48
• /
• 2022

Cyberattacks around the world continue to increase, and their damage extends beyond government facilities and affects civilians. These issues emphasized the importance of developing a system that can identify and detect cyber anomalies early. As above, in order to effectively identify cyber anomalies, several studies have been conducted to learn BGP (Border Gateway Protocol) data through a machine learning model and identify them as anomalies. However, BGP data is unbalanced data in which abnormal data is less than normal data. This causes the model to have a learning biased result, reducing the reliability of the result. In addition, there is a limit in that security personnel cannot recognize the cyber situation as a typical result of machine learning in an actual cyber situation. Therefore, in this paper, we investigate BGP (Border Gateway Protocol) that keeps network records around the world and solve the problem of unbalanced data by using SMOTE. After that, assuming a cyber range situation, an autoencoder classifies cyber anomalies and visualizes the classified data. By learning the pattern of normal data, the performance of classifying abnormal data with 92.4% accuracy was derived, and the auxiliary index also showed 90% performance, ensuring reliability of the results. In addition, it is expected to be able to effectively defend against cyber attacks because it is possible to effectively recognize the situation by visualizing the congested cyber space.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.4
• /
• pp.789-795
• /
• 2020

Many deaths have been reported due to the worldwide pandemic of COVID-19. In order to prevent the further spread of COVID-19, it is necessary to quickly and accurately read images of suspected patients and take appropriate measures. To this end, this paper introduces a deep learning-based COVID-19 chest X-ray reading technique that can assist in image reading by providing medical staff whether a patient is infected. First of all, in order to learn the reading model, a sufficient dataset must be secured, but the currently provided COVID-19 open dataset does not have enough image data to ensure the accuracy of learning. Therefore, we solved the image data number imbalance problem that degrades AI learning performance by using a Stacked Generative Adversarial Network(StackGAN++). Next, the DenseNet-based classification model was trained using the augmented data set to develop the reading model. This classification model is a model for binary classification of normal chest X-ray and COVID-19 chest X-ray, and the performance of the model was evaluated using part of the actual image data as test data. Finally, the reliability of the model was secured by presenting the basis for judging the presence or absence of disease in the input image using Grad-CAM, one of the explainable artificial intelligence called XAI.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.4
• /
• pp.647-660
• /
• 2022

Recent works demonstrate that the semi-supervised anomaly detection method functions quite well in the environment with normal data and some anomalous data. However, abnormal data shortages can occur in an environment where it is difficult to reserve anomalous data, such as an unknown attack in the cyber security fields. In this paper, we propose ADA-PH(Abnormal Data Augmentation Method using Perturbation based on Hypersphere), a novel anomalous data augmentation method that is applicable in an environment where abnormal data is insufficient to secure the performance of the semi-supervised anomaly detection method. ADA-PH generates abnormal data by perturbing samples located relatively far from the center of the hypersphere. With the network intrusion detection datasets where abnormal data is rare, ADA-PH shows 23.63% higher AUC performance than anomaly detection without data augmentation and even performs better than the other augmentation methods. Also, we further conduct quantitative and qualitative analysis on whether generated abnormal data is anomalous.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.904-905
• /
• 2023

본 논문에서는 의료 영상 생성을 위한 Med-StyleGAN2를 제안한다. 생성적 적대 신경망은 이미지 생성에는 효과적이지만, 의료 영상 생성에는 한계점을 가지고 있다. 따라서 본 연구에서는 의료 영상 생성에 특화된 StyleGAN 기반 학습 모델을 제안한다. 이는 다양한 의료 영상 어플리케이션에 활용할 수 있으며, 생성된 의료 영상에 대한 정량적, 정성적 평가를 수행함으로써 의료 영상 생성 분야의 발전 가능성에 대해 연구한다.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.1
• /
• pp.9-18
• /
• 2021

Although Generative Adversarial Networks (GANs) have gained great popularity in computer vision and related fields, generating audio signals independently has yet to be presented. Unlike images, an audio signal is a sampled signal consisting of discrete samples, so it is not easy to learn the signals using CNN architectures, which is widely used in image generation tasks. In order to overcome this difficulty, GAN researchers proposed a strategy of applying time-frequency representations of audio to existing image-generating GANs. Following this strategy, we propose an improved method for increasing the fidelity of synthesized audio signals generated by using GANs. Our method is demonstrated on a public speech dataset, and evaluated by Fréchet Inception Distance (FID). When employing our method, the FID showed 10.504, but 11.973 as for the existing state of the art method (lower FID indicates better fidelity).

• Convergence Security Journal
• /
• v.24 no.2
• /
• pp.9-17
• /
• 2024

This paper examines the security threats to enterprise Generative Artificial Intelligence systems and proposes countermeasures. As AI systems handle vast amounts of data to gain a competitive edge, security threats targeting AI systems are rapidly increasing. Since AI security threats have distinct characteristics compared to traditional human-oriented cybersecurity threats, establishing an AI-specific response system is urgent. This study analyzes the importance of AI system security, identifies key threat factors, and suggests technical and managerial countermeasures. Firstly, it proposes strengthening the security of IT infrastructure where AI systems operate and enhancing AI model robustness by utilizing defensive techniques such as adversarial learning and model quantization. Additionally, it presents an AI security system design that detects anomalies in AI query-response processes to identify insider threats. Furthermore, it emphasizes the establishment of change control and audit frameworks to prevent AI model leakage by adopting the cyber kill chain concept. As AI technology evolves rapidly, by focusing on AI model and data security, insider threat detection, and professional workforce development, companies can improve their digital competitiveness through secure and reliable AI utilization.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.9
• /
• pp.63-69
• /
• 2020

Image-image translation is a technology that creates a target image through input images, and has recently shown high performance in creating a more realistic image by utilizing GAN, which is a non-map learning structure. Therefore, there are various studies on image-to-image translation using GAN. At this point, most image-to-image translations basically target one attribute translation. But the data used and obtainable in real life consist of a variety of features that are hard to explain with one feature. Therefore, if you aim to change multiple attributes that can divide the image creation process by attributes to take advantage of the various attributes, you will be able to play a better role in image-to-image translation. In this paper, we propose Multi CycleGAN, a dual attribute transformation structure, by utilizing CycleGAN, which showed high performance among image-image translation structures using GAN. This structure implements a dual transformation structure in which three domains conduct two-way learning to learn about the two properties of an input domain. Experiments have shown that images through the new structure maintain the properties of the input area and show high performance with the target properties applied. Using this structure, it is possible to create more diverse images in the future, so we can expect to utilize image generation in more diverse areas.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.2
• /
• pp.88-95
• /
• 1999

Stack filters are a class of digital nonlinear filters with excellent properties for signal restoration. Unfortunately, present algorithms for designing stack filters with large window size are limited in applications by their computational overhead and serial nature. In this paper, new, highly-parallel algorithm is developed for determining a stack filter which minimizes the mean absolute error criterion. It retains the iterative nature of the present adaptive algorithm, but significantly reduces the number of required to converge to an optima filter. A proof is also give that the proposed algorithm converges to an optimal stack filter.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.942-945
• /
• 2019

현재 딥러닝은 컴퓨터 분야에서 이미지 처리 방법으로 활용도가 높아지면서 딥러닝 모델 개발 연구가 활발히 진행되고 있다. 딥러닝 모델 중에서 이미지 생성모델은 대표적으로 GAN(Generative Adversarial Network, 생성적 적대 신경망) 모델을 활용하고 있다. GAN은 생성기 네트워크와 판별기 네트워크를 이용하여 진짜 같은 이미지를 생성한다. 생성된 이미지는 실제 이미지와의 오차를 최소화해야 하며 이때 사용하는 함수를 손실함수라고 한다. GAN에서 손실함수는 이미지를 생성하는 학습이 불안정하여 이미지 품질이 떨어지는 문제가 있다. 개선된 GAN 관련 연구가 진행되고 있지만 완전한 문제 해결에는 부족하다. 본 논문은 7개의 GAN 모델에서 사용하는 손실함수를 분류하고 특징을 분석한다.

• Smart Media Journal
• /
• v.10 no.1
• /
• pp.63-69
• /
• 2021

When a person sees a sentence and understands the sentence, the person understands the sentence by reminiscent of the main word in the sentence as an image. Text-to-image is what allows computers to do this associative process. The previous deep learning-based text-to-image model extracts text features using Convolutional Neural Network (CNN)-Long Short Term Memory (LSTM) and bi-directional LSTM, and generates an image by inputting it to the GAN. The previous text-to-image model uses basic embedding in text feature extraction, and it takes a long time to train because images are generated using several modules. Therefore, in this research, we propose a method of extracting features by using the attention mechanism, which has improved performance in the natural language processing field, for sentence embedding, and generating an image by inputting the extracted features into the GAN. As a result of the experiment, the inception score was higher than that of the model used in the previous study, and when judged with the naked eye, an image that expresses the features well in the input sentence was created. In addition, even when a long sentence is input, an image that expresses the sentence well was created.