• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.6
• /
• pp.1215-1225
• /
• 2021

Although Artificial Intelligence (AI) techniques have shown impressive performance in various fields, they are vulnerable to adversarial examples which induce misclassification by adding human-imperceptible perturbations to the input. Previous studies to defend the adversarial examples can be classified into three categories: (1) model retraining methods; (2) input transformation methods; and (3) adversarial examples detection methods. However, even though the defense methods against adversarial examples have constantly been proposed, there is no research to classify the type of adversarial attack. In this paper, we proposed an adversarial attack family classification method based on dimensionality reduction and clustering. Specifically, after extracting adversarial perturbation from adversarial example, we performed Linear Discriminant Analysis (LDA) to reduce the dimensionality of adversarial perturbation and performed K-means algorithm to classify the type of adversarial attack family. From the experimental results using MNIST dataset and CIFAR-10 dataset, we show that the proposed method can efficiently classify five tyeps of adversarial attack(FGSM, BIM, PGD, DeepFool, C&W). We also show that the proposed method provides good classification performance even in a situation where the legitimate input to the adversarial example is unknown.

• Journal of the Korea Institute of Building Construction
• /
• v.22 no.6
• /
• pp.619-630
• /
• 2022

The concrete mix design and compressive strength evaluation are used as basic data for the durability of sustainable structures. However, the recent diversification of mixing factors has created difficulties in calculating the correct mixing factor or setting the reference value concrete mixing design. The purpose of this study is to design a predictive model of bidirectional analysis that calculates the mixing elements of ternary concrete using deep learning, one of the artificial intelligence techniques. For the DNN-based predictive model for calculating the concrete mixing factor, performance evaluation and comparison were performed using a total of 8 models with the number of layers and the number of hidden neurons as variables. The combination calculation result was output. As a result of the model's performance evaluation, an average error rate of about 1.423% for the concrete compressive strength factor was achieved. and an average MAPE error of 8.22% for the prediction of the ternary concrete mixing factor was satisfied. Through comparing the performance evaluation for each structure of the DNN model, the DNN5L-2048 model showed the highest performance for all compounding factors. Using the learned DNN model, the prediction of the ternary concrete formulation table with the required compressive strength of 30 and 50 MPa was carried out. The verification process through the expansion of the data set for learning and a comparison between the actual concrete mix table and the DNN model output concrete mix table is necessary.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.12
• /
• pp.29-40
• /
• 2022

In this paper, we studied a system that detects and analyzes the pathological features of diabetic retinopathy using Mask R-CNN and a Random Forest classifier. Those are one of the deep learning techniques and automatically diagnoses diabetic retinopathy. Diabetic retinopathy can be diagnosed through fundus images taken with special equipment. Brightness, color tone, and contrast may vary depending on the device. Research and development of an automatic diagnosis system using artificial intelligence to help ophthalmologists make medical judgments possible. This system detects pathological features such as microvascular perfusion and retinal hemorrhage using the Mask R-CNN technique. It also diagnoses normal and abnormal conditions of the eye by using a Random Forest classifier after pre-processing. In order to improve the detection performance of the Mask R-CNN algorithm, image augmentation was performed and learning procedure was conducted. Dice similarity coefficients and mean accuracy were used as evaluation indicators to measure detection accuracy. The Faster R-CNN method was used as a control group, and the detection performance of the Mask R-CNN method through this study showed an average of 90% accuracy through Dice coefficients. In the case of mean accuracy it showed 91% accuracy. When diabetic retinopathy was diagnosed by learning a Random Forest classifier based on the detected pathological symptoms, the accuracy was 99%.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.4
• /
• pp.251-260
• /
• 2022

Although the number of trees affected by pine wilt disease is decreasing, the affected area is expanding across the country. Recently, with the development of deep learning technology, it is being rapidly applied to the detection study of pine wilt nematodes and dead trees. The purpose of this study is to efficiently acquire deep learning training data and acquire accurate true values to further improve the detection ability of U-Net models through learning. To achieve this purpose, by using a filtering method applying a step-by-step deep learning algorithm the ambiguous analysis basis of the deep learning model is minimized, enabling efficient analysis and judgment. As a result of the analysis the U-Net model using the true values analyzed by period in the detection and performance improvement of dead pine trees of wilt nematode using the U-Net algorithm had a recall rate of -0.5%p than the U-Net model using the previously provided true values, precision was 7.6%p and F-1 score was 4.1%p. In the future, it is judged that there is a possibility to increase the precision of wilt detection by applying various filtering techniques, and it is judged that the drone surveillance method using drone orthographic images and artificial intelligence can be used in the pine wilt nematode disaster prevention project.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.355-364
• /
• 2023

As advanced cyber threats continue to increase in recent years, it is difficult to detect new types of cyber attacks with existing pattern or signature-based intrusion detection method. Therefore, research on anomaly detection methods using data learning-based artificial intelligence technology is increasing. In addition, supervised learning-based anomaly detection methods are difficult to use in real environments because they require sufficient labeled data for learning. Research on an unsupervised learning-based method that learns from normal data and detects an anomaly by finding a pattern in the data itself has been actively conducted. Therefore, this study aims to extract a latent vector that preserves useful sequence information from sequence log data and develop an anomaly detection learning model using the extracted latent vector. Word2Vec was used to create a dense vector representation corresponding to the characteristics of each sequence, and an unsupervised autoencoder was developed to extract latent vectors from sequence data expressed as dense vectors. The developed autoencoder model is a recurrent neural network GRU (Gated Recurrent Unit) based denoising autoencoder suitable for sequence data, a one-dimensional convolutional neural network-based autoencoder to solve the limited short-term memory problem that GRU can have, and an autoencoder combining GRU and one-dimensional convolution was used. The data used in the experiment is time-series-based NGIDS (Next Generation IDS Dataset) data, and as a result of the experiment, an autoencoder that combines GRU and one-dimensional convolution is better than a model using a GRU-based autoencoder or a one-dimensional convolution-based autoencoder. It was efficient in terms of learning time for extracting useful latent patterns from training data, and showed stable performance with smaller fluctuations in anomaly detection performance.

• 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.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.27-30
• /
• 2022

The plasma process, which has many advantages in terms of efficiency and environment compared to conventional process methods, is widely used in semiconductor manufacturing. Plasma Sheath is a dark region observed between the plasma bulk and the chamber wall surrounding it or the electrode. The Plasma Sheath Monitoring Sensor (PSMS) measures the difference in voltage between the plasma and the electrode and the RF power applied to the electrode in real time. The PSMS data, therefore, are expected to have a high correlation with the state of plasma in the plasma chamber. In this study, a model for predicting the state of nitrogen ions in the plasma chamber is training by a deep learning machine learning techniques using PSMS data. For the data used in the study, PSMS data measured in an experiment with different power and pressure settings were used as training data, and the ratio, flux, and density of nitrogen ions measured in plasma bulk and Si substrate were used as labels. The results of this study are expected to be the basis of artificial intelligence technology for the optimization of plasma processes and real-time precise control in the future.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.3
• /
• pp.103-110
• /
• 2023

With the spread of the Internet, anonymous communities emerged along with the activation of communities for communication between people, and many users are doing harm to others, such as posting aggressive posts and leaving comments using anonymity. In the past, administrators directly checked posts and comments, then deleted and blocked them, but as the number of community users increased, they reached a level that managers could not continue to monitor. Initially, word filtering techniques were used to prevent malicious writing from being posted in a form that could not post or comment if a specific word was included, but they avoided filtering in a bypassed form, such as using similar words. As a way to solve this problem, deep learning was used to monitor posts posted by users in real-time, but recently, the community uses words that can only be understood by the community or from a human perspective, not from a general Korean word. There are various types and forms of characters, making it difficult to learn everything in the artificial intelligence model. Therefore, in this paper, we proposes a preprocessing technique in which each character of a sentence is imaged using a CNN model that learns the consonants, vowel and spacing images of Korean word and converts characters that can only be understood from a human perspective into characters predicted by the CNN model. As a result of the experiment, it was confirmed that the performance of the LSTM, BiLSTM and CNN-BiLSTM models increased by 3.2%, 3.3%, and 4.88%, respectively, through the proposed preprocessing technique.

• Journal of the Korean Geotechnical Society
• /
• v.38 no.3
• /
• pp.35-42
• /
• 2022

The N-value from the Standard Penetration Test (SPT), which is one of the representative in-situ test, is an important index that provides basic geological information and the depth of the bearing layer for the design of geotechnical structures. In the aspect of time and cost-effectiveness, there is a need to carry out a representative sampling test. However, the various variability and uncertainty are existing in the soil layer, so it is difficult to grasp the characteristics of the entire field from the limited test results. Thus the spatial interpolation techniques such as Kriging and IDW (inverse distance weighted) have been used for predicting unknown point from existing data. Recently, in order to increase the accuracy of interpolation results, studies that combine the geotechnics and deep learning method have been conducted. In this study, based on the SPT results of about 22,000 holes of ground survey, a comparative study was conducted to predict the depth of the bearing layer using deep learning methods and IDW. The average error among the prediction results of the bearing layer of each analysis model was 3.01 m for IDW, 3.22 m and 2.46 m for fully connected network and PointNet, respectively. The standard deviation was 3.99 for IDW, 3.95 and 3.54 for fully connected network and PointNet. As a result, the point net deep learing algorithm showed improved results compared to IDW and other deep learning method.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.4
• /
• pp.41-51
• /
• 2023

In this paper, we propose a technique of multi-time window feature extraction for anger detection in gait data. In the previous gait-based emotion recognition methods, the pedestrian's stride, time taken for one stride, walking speed, and forward tilt angles of the neck and thorax are calculated. Then, minimum, mean, and maximum values are calculated for the entire interval to use them as features. However, each feature does not always change uniformly over the entire interval but sometimes changes locally. Therefore, we propose a multi-time window feature extraction technique that can extract both global and local features, from long-term to short-term. In addition, we also propose an ensemble model that consists of multiple classifiers. Each classifier is trained with features extracted from different multi-time windows. To verify the effectiveness of the proposed feature extraction technique and ensemble model, a public three-dimensional gait dataset was used. The simulation results demonstrate that the proposed ensemble model achieves the best performance compared to machine learning models trained with existing feature extraction techniques for four performance evaluation metrics.