• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.5
• /
• pp.871-879
• /
• 2020

Perceptual Ad-Blocking is a new advertising blocking technique that detects online advertising by using an artificial intelligence-based advertising image classification model. A recent study has shown that these Perceptual Ad-Blocking models are vulnerable to adversarial attacks using adversarial examples to add noise to images that cause them to be misclassified. In this paper, we prove that existing perceptual Ad-Blocking technique has a weakness for several adversarial example and that Defense-GAN and MagNet who performed well for MNIST dataset and CIFAR-10 dataset are good to advertising dataset. Through this, using Defense-GAN and MagNet techniques, it presents a robust new advertising image classification model for adversarial attacks. According to the results of experiments using various existing adversarial attack techniques, the techniques proposed in this paper were able to secure the accuracy and performance through the robust image classification techniques, and furthermore, they were able to defend a certain level against white-box attacks by attackers who knew the details of defense techniques.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.7
• /
• pp.37-44
• /
• 2021

Automatic classification of brain MRI images play an important role in early diagnosis of brain tumors. In this work, we present a deep learning-based brain tumor classification model in MRI images using ensemble of deep features. In our proposed framework, three different deep features from brain MR image are extracted using three different pre-trained models. After that, the extracted deep features are fed to the classification module. In the classification module, the three different deep features are first fed into the fully-connected layers individually to reduce the dimension of the features. After that, the output features from the fully-connected layers are concatenated and fed into the fully-connected layer to predict the final output. To evaluate our proposed model, we use openly accessible brain MRI dataset from web. Experimental results show that our proposed model outperforms other machine learning-based models.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.31-34
• /
• 2024

태양광 에너지는 탄소 중립 이행을 위한 주요 방안으로 많은 주목을 받고 있다. 태양광 발전량은 여러 환경적 요인에 따라 크게 달라질 수 있으므로, 정확한 발전량 예측은 전력 네트워크의 안정성과 효율적인 에너지 관리에 근본적으로 중요하다. 대표적인 인공지능 기술인 신경망(Neural Network)은 불안정한 환경 변수와 복잡한 상호작용을 효과적으로 학습할 수 있어 태양광 발전량 예측에서 우수한 성능을 도출하였다. 하지만, 신경망은 모델의 구조나 초매개변수(Hyperparameter)를 최적화하는 것은 복잡하고 시간이 많이 드는 작업이므로, 에너지 분야에서 실제 산업 적용에 한계가 존재한다. 본 논문은 2단계 신경망 최적화를 통한 태양광 발전량 예측 기법을 제안한다. 먼저, 태양광 발전량 데이터 셋을 훈련 집합과 평가 집합으로 분할한다. 훈련 집합에서, 각기 다른 은닉층의 개수로 구성된 여러 신경망 모델을 구성하고, 모델별로 Optuna를 적용하여 최적의 초매개변숫값을 선정한다. 다음으로, 은닉층별 최적화된 신경망 모델을 이용해 훈련과 평가 집합에서는 각각 5겹 교차검증을 적용한 발전량 추정값과 예측값을 출력한다. 마지막으로, 스태킹 앙상블 방식을 채택해 기본 초매개변숫값으로 설정해도 우수한 성능을 도출하는 랜덤 포레스트를 이용하여 추정값을 학습하고, 평가 집합의 예측값을 입력으로 받아 최종 태양광 발전량을 예측한다. 인천 지역으로 실험한 결과, 제안한 방식은 모델링이 간편할 뿐만 아니라 여러 신경망 모델보다 우수한 예측 성능을 도출하였으며, 이를 바탕으로 국내 에너지 산업에 이바지할 수 있을 것으로 기대한다.

• Korean Journal of Remote Sensing
• /
• v.40 no.4
• /
• pp.351-361
• /
• 2024

Satellite imagery contains various elements such as clouds, cloud shadows, and terrain shadows. Accurately identifying and eliminating these factors that complicate satellite image analysis is essential for maintaining the reliability of remote sensing imagery. For this reason, satellites such as Landsat-8, Sentinel-2, and Compact Advanced Satellite 500-1 (CAS500-1) provide Usable Data Masks(UDMs)with images as part of their Analysis Ready Data (ARD) product. Precise detection of clouds and their shadows is crucial for the accurate construction of these UDMs. Existing cloud and their shadow detection methods are categorized into threshold-based methods and Artificial Intelligence (AI)-based methods. Recently, AI-based methods, particularly deep learning networks, have been preferred due to their advantage in handling large datasets. This study aims to analyze the applicability of constructing UDMs for high-resolution satellite images through deep learning-based cloud and their shadow detection using open-source datasets. To validate the performance of the deep learning network, we compared the detection results generated by the network with pre-existing UDMs from Landsat-8, Sentinel-2, and CAS500-1 satellite images. The results demonstrated that high accuracy in the detection outcomes produced by the deep learning network. Additionally, we applied the network to detect cloud and their shadow in KOMPSAT-3/3A images, which do not provide UDMs. The experiment confirmed that the deep learning network effectively detected cloud and their shadow in high-resolution satellite images. Through this, we could demonstrate the applicability that UDM data for high-resolution satellite imagery can be constructed using the deep learning network.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.4
• /
• pp.671-685
• /
• 2023

By applying artificial intelligence to image editing technology, it has become possible to generate high-quality images with minimal traces of manipulation. However, since these technologies can be misused for criminal activities such as dissemination of false information, destruction of evidence, and denial of facts, it is crucial to implement strong countermeasures. In this study, image file and mobile forensic artifacts analysis were conducted for detecting image manipulation. Image file analysis involves parsing the metadata of manipulated images and comparing them with a Reference DB to detect manipulation. The Reference DB is a database that collects manipulation-related traces left in image metadata, which serves as a criterion for detecting image manipulation. In the mobile forensic artifacts analysis, packages related to image editing tools were extracted and analyzed to aid the detection of image manipulation. The proposed methodology overcomes the limitations of existing graphic feature-based analysis and combines with image processing techniques, providing the advantage of reducing false positives. The research results demonstrate the significant role of such methodology in digital forensic investigation and analysis. Additionally, We provide the code for parsing image metadata and the Reference DB along with the dataset of manipulated images, aiming to contribute to related research.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.1
• /
• pp.309-316
• /
• 2024

Facial recognition technology is widely used in various fields but faces challenges due to its vulnerability to fraudulent activities such as photo spoofing. Extensive research has been conducted to overcome this challenge. Most of them, however, require the use of specialized equipment like multi-modal cameras or operation in high-performance environments. In this paper, we introduce LH-FAS v2 (: Lightweight Head-pose-based Face Anti-Spoofing v2), a system designed to operate on a commercial webcam without any specialized equipment, to address the issue of facial recognition spoofing. LH-FAS v2 utilizes FSA-Net for head pose estimation and ArcFace for facial recognition, effectively assessing changes in head pose and verifying facial identity. We developed the VD4PS dataset, incorporating photo spoofing scenarios to evaluate the model's performance. The experimental results show the model's balanced accuracy and speed, indicating that head pose estimation-based facial anti-spoofing technology can be effectively used to counteract photo spoofing.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.1
• /
• pp.184-192
• /
• 2022

Valve internal leakage is caused by damage to the internal parts of the valve, resulting in accidents and shutdowns of the piping system. This study investigated the possibility of a real-time leak detection method using the acoustic emission (AE) signal generated from the piping system during the internal leakage of a butterfly valve. Datasets of raw time-domain AE signals were collected and postprocessed for each operation mode of the valve in a systematic manner to develop a data-driven model for the detection and classification of internal leakage, by applying machine learning algorithms. The aim of this study was to determine whether it is possible to treat leak detection as a classification problem by applying two classification algorithms: support vector machine (SVM) and convolutional neural network (CNN). The results showed different performances for the algorithms and datasets used. The SVM-based binary classification models, based on feature extraction of data, achieved an overall accuracy of 83% to 90%, while in the case of a multiple classification model, the accuracy was reduced to 66%. By contrast, the CNN-based classification model achieved an accuracy of 99.85%, which is superior to those of any other models based on the SVM algorithm. The results revealed that the SVM classification model requires effective feature extraction of the AE signals to improve the accuracy of multi-class classification. Moreover, the CNN-based classification can be a promising approach to detect both leakage and valve opening as long as the performance of the processor does not degrade.

• Journal of Internet Computing and Services
• /
• v.23 no.1
• /
• pp.125-134
• /
• 2022

The development of information communication and artificial intelligence technology requires the intelligent command and control (C2) system for Korean military, and various studies are attempted to achieve it. In particular, as a volume ofinformation in the C2 workflow increases exponentially, this study pays attention to the collaborative filtering (CF) and recommendation systems (RS) that can provide the essential information for the users of the C2 system has been developed. The RS performing information filtering in the C2 system should provide an explanatory recommendation and consider the context of the tasks and users. In this paper, we propose a contextual pre-filtering CARS framework that recommends information in the C2 workflow. The proposed framework consists of four components: 1) contextual pre-filtering that filters data in advance based on the context and relationship of the users, 2) feature selection to overcome the data sparseness that is a weak point for the CF, 3) the proposed CF with the features distances between the users used to calculate user similarity, and 4) rule-based post filtering to reflect user preferences. In order to evaluate the superiority of this study, various distance methods of the existing CF method were compared to the proposed framework with two experimental datasets in real-world. As a result of comparative experiments, it was shown that the proposed framework was superior in terms of MAE, MSE, and MSLE.

• The Journal of the Acoustical Society of Korea
• /
• v.43 no.1
• /
• pp.9-18
• /
• 2024

The importance of active sonar systems is emerging due to the quietness of underwater targets and the increase in ambient noise due to the increase in maritime traffic. However, the low signal-to-noise ratio of the echo signal due to multipath propagation of the signal, various clutter, ambient noise and reverberation makes it difficult to identify underwater targets using active sonar. Attempts have been made to apply data-based methods such as machine learning or deep learning to improve the performance of underwater target recognition systems, but it is difficult to collect enough data for training due to the nature of sonar datasets. Methods based on mathematical modeling have been mainly used to compensate for insufficient active sonar data. However, methodologies based on mathematical modeling have limitations in accurately simulating complex underwater phenomena. Therefore, in this paper, we propose a sonar signal synthesis method based on a deep neural network. In order to apply the neural network model to the field of sonar signal synthesis, the proposed method appropriately corrects the attention-based encoder and decoder to the sonar signal, which is the main module of the Tacotron model mainly used in the field of speech synthesis. It is possible to synthesize a signal more similar to the actual signal by training the proposed model using the dataset collected by arranging a simulated target in an actual marine environment. In order to verify the performance of the proposed method, Perceptual evaluation of audio quality test was conducted and within score difference -2.3 was shown compared to actual signal in a total of four different environments. These results prove that the active sonar signal generated by the proposed method approximates the actual signal.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.5
• /
• pp.169-176
• /
• 2020

Recently, deep neural networks (DNNs) have brought revolutions to many mobile and embedded devices by providing human-level machine intelligence for various applications. However, high inference accuracy of such DNNs comes at high computational costs, and, hence, there have been significant efforts to reduce computational overheads of DNNs either by compressing off-the-shelf models or by designing a new small footprint DNN architecture tailored to resource constrained devices. One notable recent paradigm in designing small footprint DNN models is sharing parameters in several layers. However, in previous approaches, the parameter-sharing techniques have been applied to large deep networks, such as ResNet, that are known to have high redundancy. In this paper, we propose a parameter-sharing method for already parameter-efficient small networks such as ShuffleNetV2. In our approach, small templates are combined with small layer-specific parameters to generate weights. Our experiment results on ImageNet and CIFAR100 datasets show that our approach can reduce the size of parameters by 15%-35% of ShuffleNetV2 while achieving smaller drops in accuracies compared to previous parameter-sharing and pruning approaches. We further show that the proposed approach is efficient in terms of latency and energy consumption on modern embedded devices.