• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.4
• /
• pp.573-582
• /
• 2020

Fuzzing is a method of testing software by randomly generating test cases. Since its introduction, a variety of fuzzing techniques have been studied. Among them, mutation-based fuzzing is an efficient method that finds real-world bugs even though it uses a simple approach such as probabilistic bit-flipping and character substitution. However, the interpreter fuzzing has difficulty in applying general mutation techniques because the interpreter requires grammar and semantic correctness input values. In this paper, we present a novel mutation-based fuzzing on JavaScript interpreters with a dynamic data flow analysis. To this end, we implement JMFuzzer that can generate various types of mutated test cases that operate normally without runtime errors in JavaScript interpreter considering syntax and semantics. As a result, we found numerous unknown vulnerabilities in the latest JavaScript interpreters. We reported all of them to the vendors.

• Journal of KIISE:Information Networking
• /
• v.37 no.4
• /
• pp.255-262
• /
• 2010

Recently, automated signature generation systems(ASGSs) have been developed in order to cope with zero-day attacks with malicious codes exploiting vulnerabilities which are not yet publically noticed. To enhance the usefulness of the signatures generated by (ASGSs) it is essential to identify signatures only with the high accuracy of intrusion detection among a number of generated signatures and to provide them to target security systems in a timely manner. This automated signature exchange, distribution, and update operations have to be performed in a secure and universal manner beyond the border of network administrations, and also should be able to eliminate the noise in a signature set which causes performance degradation of the security systems. In this paper, we present a system architecture to support the identification of high quality signatures and to share them among security systems through a scheme which can evaluate the detection accuracy of individual signatures, and also propose a set of algorithms dealing with exchanging, distributing and updating signatures. Though the experiment on a test-bed, we have confirmed that the high quality signatures are automatically saved at the level that the noise rate of a signature set is reduced. The system architecture and the algorithm proposed in the paper can be adopted to a automated signature sharing framework.

• Journal of the Korea Convergence Society
• /
• v.12 no.12
• /
• pp.65-74
• /
• 2021

Recently, studies on Korean spelling correction have been actively conducted based on machine translation and automatic noise generation. These methods generate noise and use as train and data set. This has limitation in that it is difficult to accurately measure performance because it is unlikely that noise other than the noise used for learning is included in the test set In addition, there is no practical error type standard, so the type of error used in each study is different, making qualitative analysis difficult. This paper proposes new 'error type classification' for deep learning-based Korean spelling correction research, and error analysis perform on existing commercialized Korean spelling correctors (System A, B, C). As a result of analysis, it was found the three correction systems did not perform well in correcting other error types presented in this paper other than spacing, and hardly recognized errors in word order or tense.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.1
• /
• pp.1-8
• /
• 2019

Among the methods for extracting the most appropriate information from a large amount of log data, there is a method using inductive inference. In this paper, we use SVM (Support Vector Machine), which is an excellent classification method for inductive inference, in order to determine the ranking of intrusion logs in digital forensic analysis. For this purpose, the logs of the training log set are classified into intrusion logs and normal logs. The associated words are extracted from each classified set to generate a related word dictionary, and each log is expressed as a vector based on the generated dictionary. Next, the logs are learned using the SVM. We classify test logs into normal logs and intrusion logs by using the log set extracted through learning. Finally, the recommendation orders of intrusion logs are determined to recommend intrusion logs to the forensic analyst.

• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.11
• /
• pp.281-290
• /
• 2020

With the spread of smartphones, services that want to use personalized data are increasing. In particular, healthcare-related services deal with a variety of data, and data visualization techniques are used to effectively show this. As data visualization techniques are used, interactions in visualization are also naturally emphasized. In the PC environment, since the interaction for data visualization is performed with a mouse, various filtering for data is provided. On the other hand, in the case of interaction in a mobile environment, the screen size is small and it is difficult to recognize whether or not the interaction is possible, so that only limited visualization provided by the app can be provided through a button touch method. In order to overcome the limitation of interaction in such a mobile environment, we intend to enable data visualization interactions through conversations with chatbots so that users can check individual data through various visualizations. To do this, it is necessary to convert the user's query into a query and retrieve the result data through the converted query in the database that is storing data periodically. There are many studies currently being done to convert natural language into queries, but research on converting user queries into queries based on visualization has not been done yet. Therefore, in this paper, we will focus on query generation in a situation where a data visualization technique has been determined in advance. Supported interactions are filtering on task x-axis values and comparison between two groups. The test scenario utilized data on the number of steps, and filtering for the x-axis period was shown as a bar graph, and a comparison between the two groups was shown as a line graph. In order to develop a natural language processing model that can receive requested information through visualization, about 15,800 training data were collected through a survey of 1,000 people. As a result of algorithm development and performance evaluation, about 89% accuracy in classification model and 99% accuracy in query generation model was obtained.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.46 no.2
• /
• pp.72-77
• /
• 2009

In this paper, a 3.2Gb/s clock and data recovery (CDR) circuit for a high-speed serial data communication without the reference clock is described This CDR circuit consists of 5 parts as Phase and frequency detector(PD and FD), multi-phase Voltage Controlled-Oscillator(VCO), Charge-pumps (CP) and external Loop-Filter(KF). It is adapted the PD and FD, which incorporates a half-rate bang-bang type oversampling PD and a half-rate FD that can improve pull-in range. The VCO consists of four fully differential delay cells with rail-to-rail current bias scheme that can increase the tuning range and tuning linearity. Each delay cell has output buffers as a full-swing generator and a duty-cycle mismatch compensation. This materialized CDR can achieve wide pull-in range without an extra reference clock and it can be also reduced chip area and power consumption effectively because there is no additional Phase Locked- Loop(PLL) for generating reference clock. The CDR circuit was designed for fabrication using 0.18um 1P6M CMOS process and total chip area excepted LF is $1{\times}1mm^2$. The pk-pk jitter of recovered clock is 26ps at 3.2Gb/s input data rate and total power consumes 63mW from 1.8V supply voltage according to simulation results. According to test result, the pk-pk jitter of recovered clock is 55ps at the same input data-rate and the reliable range of input data-rate is about from 2.4Gb/s to 3.4Gb/s.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.190-193
• /
• 2015

The current sea route sign system based on an electronic marine chart only has a data manufacture specification for uses at ECDIS. Therefore, it has a limitation in expressing various sea route data and falls short of productivity as it is frozen to prevent being changed for a long time. Also, it cannot satisfy requirements from high tech such as lattice structure data and time series information. Currently, although it builds each independent operation system based S-57, it has been found that it is the most important requirement from consumers that the entire monitoring system can mutually interwork by standardizing and uniting formats of all protocols. In addition, current status information and alarm system is using AIS, TRS, WCDMA telecommunication and processing all the data after saving it into each different server. Lighthouse lantern which currently has used was utilized to do a performance test of a developed system. All of created data was trasmitted through the RS-232, It is clear that the data was received by a situation monitoring system. In addition, when the data was transmitted after saving in a database, same data was ordinarily received. In this thesis, we will implemented the status information and alarm system of Marine transportation facilities which is a sea route sign system based on S-63 electronic marine chart, S/W, after uniting each different protocol and making combined system.

• 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 rehabilitation welfare engineering & assistive technology
• /
• v.11 no.1
• /
• pp.45-52
• /
• 2017

EEG signals that are the same as those that have the same disabled people. So, the EEG signals are becoming the next generation. In this paper, we propose an internet of things system that controls the indoor environment using EEG signal. The proposed system consists EEG measurement device, EEG simulation software and indoor environment control device. We use data as EEG signal data on emotional imagination condition in a comfortable state and logical imagination condition in concentrated state. The noise of measured signal is removed by the ICA algorithm and beta waves are extracted from it. then, it goes through learning and test process using SVM. The subjects were trained to improve the EEG signal accuracy through the EEG simulation software and the average accuracy were 87.69%. The EEG signal from the EEG measurement device is transmitted to the EEG simulation software through the serial communication. then the control command is generated by classifying emotional imagination condition and logical imagination condition. The generated control command is transmitted to the indoor environment control device through the Zigbee communication. In case of the emotional imagination condition, the soft lighting and classical music are outputted. In the logical imagination condition, the learning white noise and bright lighting are outputted. The proposed system can be applied to software and device control based BCI.

• The Journal of the Korea Contents Association
• /
• v.12 no.2
• /
• pp.472-482
• /
• 2012

There are many investors in the stock market, and more and more people get interested in the stock investment. In order to avoid risks and make profit in the stock investment, we have to determine several aspects using various information. That is, we have to select profitable stocks and determine appropriate buying/selling prices and holding period. This paper proposes a data mining tool for the investors' decision support. The data mining tool makes stock investors apply machine learning techniques and generate stock price prediction model. Also it helps determine buying/selling prices and holding period. It supports individual investor's own decision making using past data. Using the proposed tool, users can manage stock data, generate their own stock price prediction models, and establish trading policy via investment simulation. Users can select technical indicators which they think affect future stock price. Then they can generate stock price prediction models using the indicators and test the models. They also perform investment simulation using proper models to find appropriate trading policy consisting of buying/selling prices and holding period. Using the proposed data mining tool, stock investors can expect more profit with the help of stock price prediction model and trading policy validated on past data, instead of with an emotional decision.