• Journal of Korean Tunnelling and Underground Space Association
• /
• v.22 no.5
• /
• pp.515-528
• /
• 2020

Underground concrete structures are usually designed to be used for decades, but in recent years, many of them are nearing their original life expectancy. As a result, it is necessary to promptly inspect and repair the structure, since it can cause lost of fundamental functions and bring unexpected problems. Therefore, personnel-based inspections and repairs have been underway for maintenance of underground structures, but nowadays, objective inspection technologies have been actively developed through the fusion of deep learning and image process. In particular, various researches have been conducted on developing a concrete crack detection algorithm based on supervised learning. Most of these studies requires a large amount of image data, especially, label images. In order to secure those images, it takes a lot of time and labor in reality. To resolve this problem, we introduce a method to increase the accuracy of crack area detection, improved by 0.25% on average by applying adversarial learning in this paper. The adversarial learning consists of a segmentation neural network and a discriminator neural network, and it is an algorithm that improves recognition performance by generating a virtual label image in a competitive structure. In this study, an efficient deep neural network learning method was proposed using this method, and it is expected to be used for accurate crack detection in the future.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.450-452
• /
• 2021

본 논문은 범용의 한국어 패러프레이즈 문장 인식 모델 개발을 위한 연구를 다룬다. 범용의 목적을 위해서 가장 걸림돌이 되는 부분 중의 하나는 적대적 예제에 대한 강건성이다. 왜냐하면 패러프레이즈 문장 인식에 대한 적대적 예제는 일반 유형의 말뭉치로 학습시킨 인식 모델을 무력화 시킬 수 있기 때문이다. 또한 적대적 예제의 유형이 다양하기 때문에 다양한 유형에 대해서도 대응할 수 있어야 하는 어려운 점이 있다. 본 논문에서는 다양한 적대적 예제 유형과 일반 유형 모두에 대해서 패러프레이즈 문장 여부를 인식할 수 있는 딥 뉴럴 네트워크 모델을 제시하고자 한다.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.437-450
• /
• 2022

Generative adversarial networks(GANs) have demonstrated remarkable success in image synthesis. However, since GANs show instability in the training stage on large datasets, it is difficult to apply to various application fields. A single image GAN is a field that generates various images by learning the internal distribution of a single image. In this paper, we investigate five Single Image GAN: SinGAN, ConSinGAN, InGAN, DeepSIM, and One-Shot GAN. We compare the performance of each model and analyze the pros and cons of a single image GAN.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.3
• /
• pp.449-458
• /
• 2023

Artificial Intelligence is providing convenience in various fields using big data and deep learning technologies. However, deep learning technology is highly vulnerable to adversarial examples, which can cause misclassification of classification models. This study proposes a method to detect and purification various adversarial attacks using StarGAN. The proposed method trains a StarGAN model with added Categorical Entropy loss using adversarial examples generated by various attack methods to enable the Discriminator to detect adversarial examples and the Generator to purification them. Experimental results using the CIFAR-10 dataset showed an average detection performance of approximately 68.77%, an average purification performance of approximately 72.20%, and an average defense performance of approximately 93.11% derived from restoration and detection performance.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.67-76
• /
• 2023

Although deep learning models are making innovative achievements in the field of computer vision, the problem of vulnerability to adversarial examples continues to be raised. Adversarial examples are attack methods that inject fine noise into images to induce misclassification, which can pose a serious threat to the application of deep learning models in the real world. In this paper, we propose a model that detects adversarial examples using differences in predictive values between edge-learned classification models and underlying classification models. The simple process of extracting the edges of the objects and reflecting them in learning can increase the robustness of the classification model, and economical and efficient detection is possible by detecting adversarial examples through differences in predictions between models. In our experiments, the general model showed accuracy of {49.9%, 29.84%, 18.46%, 4.95%, 3.36%} for adversarial examples (eps={0.02, 0.05, 0.1, 0.2, 0.3}), whereas the Canny edge model showed accuracy of {82.58%, 65.96%, 46.71%, 24.94%, 13.41%} and other edge models showed a similar level of accuracy also, indicating that the edge model was more robust against adversarial examples. In addition, adversarial example detection using differences in predictions between models revealed detection rates of {85.47%, 84.64%, 91.44%, 95.47%, and 87.61%} for each epsilon-specific adversarial example. It is expected that this study will contribute to improving the reliability of deep learning models in related research and application industries such as medical, autonomous driving, security, and national defense.

• Journal of Korea Water Resources Association
• /
• v.56 no.7
• /
• pp.439-449
• /
• 2023

Recent advancements in data measuring technology have facilitated the installation of various sensors, such as pressure meters and flow meters, to effectively assess the real-time conditions of water distribution systems (WDSs). However, as cities expand extensively, the factors that impact the reliability of measurements have become increasingly diverse. In particular, demand data, one of the most significant hydraulic variable in WDS, is challenging to be measured directly and is prone to missing values, making the development of accurate data generation models more important. Therefore, this paper proposes an adversarially trained autoencoder (ATAE) model based on generative deep learning techniques to accurately estimate demand data in WDSs. The proposed model utilizes two neural networks: a generative network and a discriminative network. The generative network generates demand data using the information provided from the measured pressure data, while the discriminative network evaluates the generated demand outputs and provides feedback to the generator to learn the distinctive features of the data. To validate its performance, the ATAE model is applied to a real distribution system in Austin, Texas, USA. The study analyzes the impact of data uncertainty by calculating the accuracy of ATAE's prediction results for varying levels of uncertainty in the demand and the pressure time series data. Additionally, the model's performance is evaluated by comparing the results for different data collection periods (low, average, and high demand hours) to assess its ability to generate demand data based on water consumption levels.

• Communications of the Korean Institute of Information Scientists and Engineers
• /
• v.36 no.2
• /
• pp.9-13
• /
• 2018

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.380-382
• /
• 2019

GAN(Generative Adversarial Network)은 정해진 학습 데이터에서 정해진 생성자와 구분자가 서로 각각에게 적대적인 관계를 유지하며 동시에 서로에게 생산적인 관계를 유지하며 가능한 긍정적인 영향을 주며 학습하는 기계학습 분야이다. 전통적인 문장 생성은 단어의 통계적 분포를 기반으로 한 마르코프 결정 과정(Markov Decision Process)과 순환적 신경 모델(Recurrent Neural Network)을 사용하여 학습시킨다. 이러한 방법은 문장 생성과 같은 연속된 데이터를 기반으로 한 모델들의 표준 모델이 되었다. GAN은 표준모델이 존재하는 해당 분야에 새로운 모델로써 다양한 시도가 시도되고 있다. 하지만 이러한 모델의 시도에도 불구하고, 지금까지 해결하지 못하고 있는 다양한 문제점이 존재한다. 이 논문에서는 다음과 같은 두 가지 문제점에 집중하고자 한다. 첫째, Sequential 한 데이터 처리에 어려움을 겪는다. 둘째, 무작위로 생성하기 때문에 사용자가 원하는 데이터만 출력되지 않는다. 본 논문에서는 이러한 문제점을 해결하고자, 부분적인 정답 제공을 통한 조건별 생산적 적대 생성망을 설계하여 이 방법을 사용하여 해결하였다. 첫째, Sequence to Sequence 모델을 도입하여 Sequential한 데이터를 처리할 수 있도록 하여 원시적인 텍스트를 생성할 수 있게 하였다. 둘째, 부분적인 정답 제공을 통하여 문장의 생성 조건을 구분하였다. 결과적으로, 제안하는 기법들로 원시적인 감정 텍스트를 생성할 수 있었다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.617-619
• /
• 2018

In this paper, We suggest a face image generating GAN model which is improved by an additive discriminator. This discriminator is trained to be specialized in preventing frequent mistake of generator. To verify the model suggested, we used $^*Inception$ score. We used 155,680 images of $^*celebA$ which is frontal face. We earned average 1.742p at Inception score and it is much better score compare to previous model.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.11a
• /
• pp.123-125
• /
• 2022

본 논문에서는 판별자를 활용하여 Image to Image translation(I2I) 분야에서 사용되는 적대적 생성 신경망(GAN)을 압축하는 방법을 제시한다. 우선, 잘 학습된 판별자와 생성자 사이의 adversarial loss 를 활용하여 생성자 내 필터들의 중요도 점수를 매겨준다. 그리고 생성자 내의 필터들을 중요도 점수를 기준으로 나열한 후 점수가 낮은 필터들을 제거하는 필터 프루닝을 한번 수행하여 적은 시간 비용으로 생성자를 압축한다. 마지막으로 지식 증류를 활용해 압축된 생성자를 학습시켜 기존의 생성자와 유사한 성능을 보이도록 하였다. 이 과정들을 통해 효과적이고 빠르게 GAN 모델을 압축할 수 있음을 확인하였다.