• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.23 no.2
• /
• pp.329-337
• /
• 2013

Cyber threats of the ICS(Industrial Control System) has been researched on the level to the threat to the network service as well as a specific system, even if the extent of damage was not intended. Although some range of "security" just include the protection of systems against the deliberate attacks of terrorists or cyber hackers, often more damage is done by carelessness, and equipment failures than by those deliberate attacks. This paper presented a taxonomy for classifying all abnormal behaviors of ICS, including deliberate attacks, inadvertent mistakes, equipment failures, and software problems. The classification criteria of ICS abnormal behaviors was selected to highlight commonalities and important features of deliberate attacks as well as inadvertent actions.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.262-273
• /
• 2024

We provide a detailed analysis of the data processing and model training process for vulnerability classification using Transformer-based language models, especially sentence text-to-text transformers (ST5)-XXL and XLNet. The main purpose of this study is to compare the performance of the two models, identify the strengths and weaknesses of each, and determine the optimal learning rate to increase the efficiency and stability of model training. We performed data preprocessing, constructed and trained models, and evaluated performance based on data sets with various characteristics. We confirmed that the XLNet model showed excellent performance at learning rates of 1e-05 and 1e-04 and had a significantly lower loss value than the ST5-XXL model. This indicates that XLNet is more efficient for learning. Additionally, we confirmed in our study that learning rate has a significant impact on model performance. The results of the study highlight the usefulness of ST5-XXL and XLNet models in the task of classifying security vulnerabilities and highlight the importance of setting an appropriate learning rate. Future research should include more comprehensive analyzes using diverse data sets and additional models.

• Proceedings of the KIEE Conference
• /
• 1999.07c
• /
• pp.1373-1375
• /
• 1999

High impedance fault (HIF) is defined as fault the general overcurrent relay can not detect or interrupt. Especially when HIF occur in residential areas, energized high voltage conductor results in fire hazard, equiment damage or personal threat. This paper proposes the model of HIF in transmission line using the ZnO arrester and resistance to be implemented within EMTP. Wavelet transform is efficient and useful for the detection of HIF in power system, because it uses variable windows according to frequency. HIF detection method using wavelet transform can distinguish HIF from similar phenomena like arcfurance load, capacitor bank switching and line switching.

• Journal of Positioning, Navigation, and Timing
• /
• v.9 no.1
• /
• pp.7-13
• /
• 2020

As a countermeasure against the threat of jamming which can disrupt operation of the Global Positioning System (GPS) receivers, various kinds of technique to estimate the Direction-Of-Arrivals (DOAs) of incoming jamming signals have been widely studied, and among them, the MUltiple SIgnal Classification (MUSIC) algorithm is known to provide very high resolution. However, since the previous studies regarding the MUSIC algorithm does not consider the orientation of each antenna element of antenna arrays, there is a possibility that DOA estimation performance degrades in the case of a misaligned antenna array whose antenna elements are not oriented along the same direction. As an effort to solve this problem, there exists a previous work which presents an MUSIC-based method for DOA estimation. However, the error between the real and measured values of each antenna orientation is not taken into consideration. Therefore, in this paper, the effect of the aforementioned error on the DOA estimation performance in the case of a misaligned antenna array is analyzed by simulations.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.4
• /
• pp.1375-1384
• /
• 2014

Flashover of power transmission line insulators is a major threat to the reliable operation of power system. This paper deals with the flashover prediction of polymeric insulators used in power transmission line applications using the novel condition monitoring technique developed by PD signal time-frequency map and neural network technique. Laboratory experiments on polymeric insulators were carried out as per IEC 60507 under AC voltage, at different humidity and contamination levels using NaCl as a contaminant. Partial discharge signals were acquired using advanced ultra wide band detection system. Salient features from the Time-Frequency map and PRPD pattern at different pollution levels were extracted. The flashover prediction of polymeric insulators was automated using artificial neural network (ANN) with back propagation algorithm (BPA). From the results, it can be speculated that PD signal feature extraction along with back propagation classification is a well suited technique to predict flashover of polymeric insulators.

• Journal of Information Processing Systems
• /
• v.16 no.4
• /
• pp.882-895
• /
• 2020

The amount of malware increases exponentially every day and poses a threat to networks and operating systems. Most new malware is a variant of existing malware. It is difficult to deal with numerous malware variants since they bypass the existing signature-based malware detection method. Thus, research on automated methods of detecting and processing variant malware has been continuously conducted. This report proposes a method of extracting feature data from files and detecting malware using machine learning. Feature data were extracted from 7,000 malware and 3,000 benign files using static and dynamic malware analysis tools. A malware classification model was constructed using multiple DNN, XGBoost, and RandomForest layers and the performance was analyzed. The proposed method achieved up to 96.3% accuracy.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.1
• /
• pp.16-22
• /
• 2010

Electrocardiogram(ECG) analysis and arrhythmia recognition are critical for diagnosis and treatment of ill patients. Cardiac arrhythmia is a condition in which heart beat may be irregular and presents a serious threat to the patient recovering from ventricular tachycardia (VT) and ventricular fibrillation (VF). Other arrhythmias like atrial premature contraction (APC), Premature ventricular contraction (PVC) and superventricular tachycardia (SVT) are important in diagnosing the heart diseases. This paper presented new method to classify various arrhythmias contrary to other techniques which are limited to only two or three arrhythmias. ECG is decomposed into Intrinsic Mode Functions (IMFs) by Empirical Mode Decomposition (EMD). Burg algorithm was performed on IMFs to obtain AR coefficients which can reduce the dimension of feature vector and utilized as Multi-class SVM inputs which is basically extended from binary SVM. We chose optimal parameters for SVM classifier, applied to arrhythmias classification and achieved the accuracies of detecting NSR, APC, PVC, SVT, VT and VP were 96.8% to 99.5%. The results showed that EMD was useful for the preprocessing and feature extraction and multi-class SVM for classification of cardiac arrhythmias, with high usefulness.

• Fire Science and Engineering
• /
• v.34 no.1
• /
• pp.89-102
• /
• 2020

Chemical terrorism using toxic and flammable gases, which could be fatal to the health of the human body, poses a serious threat to the security of most advanced countries, as well as those that are suffering from local disputes, due to the asymmetric information that exists between terrorist actors and victims. The countermeasures against chemical terrorism can be roughly divided into three stages: prevention, response, and probation. The critical factors for each professional response agency, and the personnel that determine the degree and range of chemical terrorism damage, are performing missions successfully in the process of the prevention and the response stage against chemical terrorism. To do this, conducting objective and systematical assessments on facilities that could potentially be the subject of chemical terrorism is more important than anything. In this study, we compared the existing domestic and foreign vulnerable classification systems for chemical terrorism, reviewed the current direction of improvement in domestic classification systems, and suggested more scientific and systematic methodologies through the vulnerability assessment on an actual public facility sample.

• Journal of Korean Society of Environmental Engineers
• /
• v.35 no.7
• /
• pp.503-508
• /
• 2013

The aim of this study was to investigate the microbial communities in animal carcass disposal soils to examine the possible threat of pathogens from leachate. DNA extraction was performed for the soils in three carcass disposal sites located in Gyeonggi-do, Korea, and then 16S rRNA pyrosequencing was conducted to identify the microbial communities. Results indicate that, according to phylum classification, Proteobacteria (100%) was identified in soil A, Actinobacteria (66.4%) > Proteobacteria (31.1%) > Bacteriodetes (2.1%) > Acidobacteria (0.3%) in soil B, and Actinobacteria (63.1%) > Proteobacteria (36.9%) in soil C. According to genus classification, Pseudomonas was dominant in soil A (98%), Arthrobacter in soil B (68%) and C (61%). There were no detections of pathogens such as Salmonella, Campylobacter and Clostridium perfringens. However, high concentration of Ralstonia pickettii causing bacteremia was observed. Although carcass disposal soils examined in this study were not highly contaminated with pathogens, further monitoring is still needed to examine the potential threat of pathogens in leachate derived from carcass disposal sites.

• 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.