• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.2
• /
• pp.456-477
• /
• 2024

With information technology's rapid development, the Internet faces serious security problems. Studies have shown that malware has become a primary means of attacking the Internet. Therefore, adversarial samples have become a vital breakthrough point for studying malware. By studying adversarial samples, we can gain insights into the behavior and characteristics of malware, evaluate the performance of existing detectors in the face of deceptive samples, and help to discover vulnerabilities and improve detection methods for better performance. However, existing adversarial sample generation methods still need help regarding escape effectiveness and mobility. For instance, researchers have attempted to incorporate perturbation methods like Fast Gradient Sign Method (FGSM), Projected Gradient Descent (PGD), and others into adversarial samples to obfuscate detectors. However, these methods are only effective in specific environments and yield limited evasion effectiveness. To solve the above problems, this paper proposes a malware adversarial sample generation method (PixGAN) based on the pixel attention mechanism, which aims to improve adversarial samples' escape effect and mobility. The method transforms malware into grey-scale images and introduces the pixel attention mechanism in the Deep Convolution Generative Adversarial Networks (DCGAN) model to weigh the critical pixels in the grey-scale map, which improves the modeling ability of the generator and discriminator, thus enhancing the escape effect and mobility of the adversarial samples. The escape rate (ASR) is used as an evaluation index of the quality of the adversarial samples. The experimental results show that the adversarial samples generated by PixGAN achieve escape rates of 97%, 94%, 35%, 39%, and 43% on the Random Forest (RF), Support Vector Machine (SVM), Convolutional Neural Network (CNN), Convolutional Neural Network and Recurrent Neural Network (CNN_RNN), and Convolutional Neural Network and Long Short Term Memory (CNN_LSTM) algorithmic detectors, respectively.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_4
• /
• pp.1179-1194
• /
• 2020

This study investigates the feasibility of three algorithms, K-Nearest Neighbors (K-NN), Random Forest (RF) and Neural Network (NN), for estimating the air temperature of an unobserved area where the weather station is not installed. The satellite image were obtained from Landsat-8 and MODIS Aqua/Terra acquired in 2019, and the meteorological ground weather data were from AWS/ASOS data of Korea Meteorological Administration and Korea Forest Service. In addition, in order to improve the estimation accuracy, a digital surface model, solar radiation, aspect and slope were used. The accuracy assessment of machine learning methods was performed by calculating the statistics of R² (determination coefficient) and Root Mean Square Error (RMSE) through 10-fold cross-validation and the estimated values were compared for each target area. As a result, the neural network algorithm showed the most stable result among the three algorithms with R² = 0.805 and RMSE = 0.508. The neural network algorithm was applied to each data set on Landsat imagery scene. It was possible to generate an mean air temperature map from June to September 2019 and confirmed that detailed air temperature information could be estimated. The result is expected to be utilized for national disaster safety management such as heat wave response policies and heat island mitigation research.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2012.02a
• /
• pp.478-478
• /
• 2012

Recently, there are many researches in order to increase the deposition rate (D/R) and improve film uniformity and quality in the deposition of microcrystalline silicon thin film. These two factors are the most important issues in the fabrication of the thin film solar cell, and for the purpose of that, several process conditions, including the large area electrode (more than 1.1 X 1.3 (m2)), higher pressure (1 ~ 10 (Torr)), and very high frequency regime (VHF, 40 ~ 100 (MHz)), have been needed. But, in the case of large-area capacitively coupled discharges (CCP) driven at frequencies higher than the usual RF (13.56 (MHz)) frequency, the standing wave and skin effects should be the critical problems for obtaining the good plasma uniformity, and the ion damage on the thin film layer due to the high voltage between the substrate and the bulk plasma might cause the defects which degrade the film quality. In this study, we will propose the new concept of the large-area multi-electrode (a new multi-electrode concept for the large-area plasma source), which consists of a series of electrodes and grounds arranged by turns. The experimental results with this new electrode showed the processing performances of high D/R (1 ~ 2 (nm/sec)), controllable crystallinity (~70% and controllable), and good uniformity (less than 10%) at the conditions of the relatively high frequency of 40 MHz in the large-area electrode of 280 X 540 mm2. And, we also observed the SEM images of the deposited thin film at the conditions of peeling, normal microcrystalline, and powder formation, and discussed the mechanisms of the crystal formation and voids generation in the film in order to try the enhancement of the film quality compared to the cases of normal VHF capacitive discharges. Also, we will discuss the relation between the processing parameters (including gap length between electrode and substrate, operating pressure) and the processing results (D/R and crystallinity) with the process condition map for ${\mu}c$-Si:H formation at a fixed input power and gas flow rate. Finally, we will discuss the potential of the multi-electrode of the 3.5G-class large-area plasma processing (650 X 550 (mm2) to the possibility of the expansion of the new electrode concept to 8G class large-area plasma processing and the additional issues in order to improve the process efficiency.

• Journal of Biomedical Engineering Research
• /
• v.27 no.5
• /
• pp.203-209
• /
• 2006

The aim of this study is to investigate the feasibility of ex vivo MR diffusion tensor imaging technique in order to observe the diffusion-contrast characteristics of human gastric tissues. On normal and pathologic gastric tissues, which have been fixed in a polycarbonate plastic tube filled with 10% formalin solution, laboratory made 3D diffusion tensor Turbo FLASH pulse sequence was used to obtain high resolution MR images with voxel size of $0.5{\times}0.5{\times}0.5mm^3\;using\;64{\times}32{\times}32mm^3$ field of view in conjunction with an acquisition matrix of $128{\times}64{\times}64$. Diffusion weighted- gradient pulses were employed with b values of 0 and $600s/mm^2$ in 6 orientations. The sequence was implemented on a clinical 3.0-T MRI scanner(Siemens, Erlangen, Germany) with a home-made quadrature-typed birdcage Tx/Rx rf coil for small specimen. Diffusion tensor values in each pixel were calculated using linear algebra and singular value decomposition(SVD) algorithm. Apparent diffusion coefficient(ADC) and fractional anisotropy(FA) map were also obtained from diffusion tensor data to compare pixel intensities between normal and abnormal gastric tissues. The processing software was developed by authors using Visual C++(Microsoft, WA, U.S.A.) and mathematical/statistical library of GNUwin32(Free Software Foundation). This study shows that 3D diffusion tensor Turbo FLASH sequence is useful to resolve fine micro-structures of gastric tissue and both ADC and FA values in normal gastric tissue are higher than those in abnormal tissue. Authors expect that this study also represents another possibility of gastric carcinoma detection by visualizing diffusion characteristics of proton spins in the gastric tissues.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_3
• /
• pp.1109-1123
• /
• 2020

In South Korea with forest as a major land cover class (over 60% of the country), many wildfires occur every year. Wildfires weaken the shear strength of the soil, forming a layer of soil that is vulnerable to landslides. It is important to identify the severity of a wildfire as well as the burned area to sustainably manage the forest. Although satellite remote sensing has been widely used to map wildfire severity, it is often difficult to determine the severity using only the temporal change of satellite-derived indices such as Normalized Difference Vegetation Index (NDVI) and Normalized Burn Ratio (NBR). In this study, we proposed an approach for determining wildfire severity based on machine learning through the synergistic use of Sentinel-1A Synthetic Aperture Radar-C data and Sentinel-2A Multi Spectral Instrument data. Three wildfire cases-Samcheok in May 2017, Gangreung·Donghae in April 2019, and Gosung·Sokcho in April 2019-were used for developing wildfire severity mapping models with three machine learning algorithms (i.e., Random Forest, Logistic Regression, and Support Vector Machine). The results showed that the random forest model yielded the best performance, resulting in an overall accuracy of 82.3%. The cross-site validation to examine the spatiotemporal transferability of the machine learning models showed that the models were highly sensitive to temporal differences between the training and validation sites, especially in the early growing season. This implies that a more robust model with high spatiotemporal transferability can be developed when more wildfire cases with different seasons and areas are added in the future.