• Journal of the Korea Society of Computer and Information
• /
• v.25 no.11
• /
• pp.131-138
• /
• 2020

Malware is generally recognized as a computer program that penetrates another computer system and causes malicious behavior intended by the developer. In cyberspace, it is also used as a cyber weapon to attack adversary. The most important factor that a malware must have as a cyber weapon is that it must achieve its intended purpose before being detected by the other's detection system. It requires a lot of time and expertise to create a single malware to avoid the other's detection system. We propose the framework that automatically generates variant malware when a binary code type malware is input using the DCM technique. In this framework, the sample malware was automatically converted into variant malware, and it was confirmed that this variant malware was not detected in the signature-based malware detection system.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.10B
• /
• pp.1233-1239
• /
• 2011

The visible light convergence communication technology is suitable for indoor wireless communication and digital lighting fixtures, it could be used as lighting devices as well as a communication device. However, because that VLC is the technology of came to world a few years ago, there are many problems which had to solve. The signal sensing of VLC transmitter is one of the most challenging issue in VLC systems. Therefore in this paper, we analysis the performance of various sensing scheme for efficient detection of VLC systems. The signal of user is OFDM signal and the wirelss channel between a user and VLC system is modeled as indoor VLC channel. From the simulation results, it is confirmed that the proposed scheme is very effective to signal sensing for VLC systems.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.1
• /
• pp.63-68
• /
• 2021

Recently there is sharply increasing interest in watching and creating video contents such as YouTube. However, creating such video contents without privacy protection technique can expose other people in the background in public, which is consequently violating their privacy rights. This paper seeks to remedy these problems and proposes a technique that identifies faces and protecting portrait rights by blurring the face. The key contribution of this paper lies on our deep-learning technique with low detection error and high computation that allow to protect portrait rights in real-time videos. To reduce errors, an efficient tracking algorithm was used in this system with face detection and face recognition algorithm. This paper compares the performance of the proposed system with and without the tracking algorithm. We believe this system can be used wherever the video is used.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.4008-4023
• /
• 2022

Since machine learning was introduced into cross-site scripting (XSS) attack detection, many researchers have conducted related studies and achieved significant results, such as saving time and labor costs by not maintaining a rule database, which is required by traditional XSS attack detection methods. However, this topic came across some problems, such as poor generalization ability, significant false negative rate (FNR) and false positive rate (FPR). Moreover, the automatic clustering property of graph convolutional networks (GCN) has attracted the attention of researchers. In the field of natural language process (NLP), the results of graph embedding based on GCN are automatically clustered in space without any training, which means that text data can be classified just by the embedding process based on GCN. Previously, other methods required training with the help of labeled data after embedding to complete data classification. With the help of the GCN auto-clustering feature and labeled data, this research proposes an approach to detect XSS attacks (called GCNXSS) to mine the dependencies between the units that constitute an XSS payload. First, GCNXSS transforms a URL into a word homogeneous graph based on word co-occurrence relationships. Then, GCNXSS inputs the graph into the GCN model for graph embedding and gets the classification results. Experimental results show that GCNXSS achieved successful results with accuracy, precision, recall, F1-score, FNR, FPR, and predicted time scores of 99.97%, 99.75%, 99.97%, 99.86%, 0.03%, 0.03%, and 0.0461ms. Compared with existing methods, GCNXSS has a lower FNR and FPR with stronger generalization ability.

• Smart Media Journal
• /
• v.12 no.11
• /
• pp.1-9
• /
• 2023

Stress is a significant issue in modern society, often triggered by external or internal factors that are difficult to manage. When high stress persists over a long term, it can develop into a chronic condition, negatively impacting health and overall well-being. However, it is challenging for individuals experiencing chronic stress to recognize their condition, making early detection and management crucial. Using biosignals measured from wearable devices to detect stress could lead to more effective management. However, there are two main problems with using biosignals: first, manually extracting features from these signals can introduce bias, and second, the performance of classification models can vary greatly depending on the subject of the experiment. This paper proposes a model that reduces bias using convo utional autoencoders, which can represent the key features of data, and enhances generalizability by employing soft voting, a method of ensemble learning, to minimize performance variability. To verify the generalization performance of the model, we evaluate it using LOSO cross-validation method. The model proposed in this paper has demonstrated superior accuracy compared to previous studies using the WESAD dataset.

• The Korean Journal of Applied Statistics
• /
• v.22 no.6
• /
• pp.1191-1201
• /
• 2009

The cumulative sum(CUSUM) control charts are typically used for detecting small level shifts in process control. To control an auto-correlated process, the model-based control methods can be employed, in which the residuals from fitting a time series model are applied to the CUSUM chart. However, the persistent level shifts in the original process may lead to varying mean shifts in residuals, which may deteriorate detection performance significantly. Therefore, in this paper, focussing on ARMA(1,1), we propose a new CUSUM type control method which can detect the dynamic mean shifts in residuals especially with oscillating pattern effectively and, through the simulation study, evaluate its performance by comparing with other various CUSUM type control methods introduced so far.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.1
• /
• pp.159-165
• /
• 2010

The moving object monitoring and transforming personal robot system based on remote controls is designed and implemented, and the performance of the system is analyzed in this paper. The major considering factors in the system design are such as 1) the control scheme design (button based and the remote control schemes); 2) the operation modes design (wheel driving mode/pedestrian mode/auto driving mode/observation mode); 3) the remote control function design; 4) the design of the monitoring function of the changes in neighbor environments; 5) the design of the detection of obstruction. From the experiments, it is assured that the developed personal robot can walk to the grounds that covered with doorsill or electric wires in indoors by control the leg articulations, and can escape from the obstruction using three infrared sensors in the 30cm*30cm obstruction styled space under the auto driving mode.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.44 no.3
• /
• pp.45-50
• /
• 2007

We present a auto compensating quantum key distribution system based on optical fiber at 1550nm. In the quantum key transmission system, main control board and phase modulation driving board are fabricated for auto controlling quantum key distribution(QKD). We tested the single photon counts per dark counts for a single photon detector, quantum key distribution rate($R_{sift}$) and the quantum bit error rate (QBER). Quantum bit error rate of 3.5% in 25km QKD is obtained. This system is commercially available.

• Journal of Auto-vehicle Safety Association
• /
• v.5 no.1
• /
• pp.44-49
• /
• 2013

This paper presents a lateral collision risk index between an ego vehicle and a rear-side vehicle. The lateral collision risk is designed to represent a lateral collision risk and provide the appropriate threshold value of activation of the lateral collision management system such as the Blind Spot Detection(BSD). The lateral collision risk index is designed using the Time to Line Crossing(TLC) and the longitudinal collision index at the predicted TLC. TLC and the longitudinal collision index are calculated with the signals from the exterior sensor such as the radar equipped on the rear-side of a vehicle and a vision sensor which detects the distance and time to the lane departure. For the robust situation assessment, the perception of driving environment determining whether the road is straighten or curved should be determined. The relative motion estimation method has been proposed with the road information via the integrated estimator using the environment sensors and vehicle sensor. A lateral collision risk index was composed with the estimated relative motion considering the relative yaw angle. The performance of the proposed lateral collision risk index is investigated via computer simulations conducted using the vehicle dynamics software CARSIM and Matlab/Simulink.

• Journal of Animal Environmental Science
• /
• v.9 no.1
• /
• pp.45-56
• /
• 2003

$TAO^{TM}$ System is an auto-heated thermophilic aerated digestion process using a proprietary microbe called as a Phototropic Bacteria (PTB). High metabolic activity results in heat generation, which enables to produce a pathogen-free and digested liquid fertilizer at short retention times. TAO$^{TM}$ system has been developed to reduce a manure volume and convert into the liquid fertilizer using swine manure since 1992. About 100 units have been installed and operated in Korean swine farms so far. TAO$^{TM}$ system consists of a reactor vessel and ejector-type aeration pumps and foam removers. The swine slurry manure enters into vessel with PTB and is mixed and aerated. The process is operated at detention times from 2 to 4 days and temperature of 55 to $65^{\circ}C$. Foams are occurred and broken down by foam removers to evaporate water contents. Generally, at least 30% of water content is evaporated, 99% of volatile fatty acids caused an odor are removed and pathogen destruction is excellent with fecal coliform, rotavirus and salmonella below detection limits. The effluent from TAO$^{TM}$ system, called as the "TAO EFFLUX", is screened and has superb properties as a fertilizer. Normally N-P-K contents of screened TAO Efflux are 4.7 g/L, 0.375 g/L and 2.8 g/L respectively. The fertilizer effect of TAO EFFLUX compared to chemical fertilizer has been demonstrated and studied with various crops such as rice, potato, cabbage, pumpkin, green pepper, parsley, cucumber and apple. Generally it has better fertilizer effects and excellent soil fertility improvement effects. Moreover, the TAO EFFLUX is concentrated through membrane technology without fouling problems for a cost saving of long distance transportation and a commercialization (crop nutrient commodity) to a gardening market, for example.