• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.3
• /
• pp.403-416
• /
• 2024

Malware is being commercialized and sold on the black market, primarily driven by financial incentives. With the increasing demand driven by these sales, the scope of attacks via malware has expanded. In response, there has been a surge in research efforts leveraging artificial intelligence for detection and classification. However, adversaries are integrating various anti-analysis techniques into their malware to thwart analytical efforts. In this study, we introduce the "Malware Analysis with Dynamic Extraction (MADE)" framework, a hybrid binary analysis tool devised to procure datasets from advanced malware incorporating Anti-Analysis techniques. The MADE framework has the proficiency to autonomously execute dynamic analysis on binaries, encompassing those laden with Anti-VM and Anti-Debugging defenses. Experimental results substantiate that the MADE framework can effectively circumvent over 90% of diverse malware implementations using Anti-Analysis techniques and can adeptly extract relevant datasets.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.4
• /
• pp.166-173
• /
• 2024

This study explores lip-sync detection, focusing on the synchronization between lip movements and voices in videos. Typically, lip-sync detection techniques involve cropping the facial area of a given video, utilizing the lower half of the cropped box as input for the visual encoder to extract visual features. To enhance the emphasis on the articulatory region of lips for more accurate lip-sync detection, we propose utilizing a pre-trained visual attention-based encoder. The Visual Transformer Pooling (VTP) module is employed as the visual encoder, originally designed for the lip-reading task, predicting the script based solely on visual information without audio. Our experimental results demonstrate that, despite having fewer learning parameters, our proposed method outperforms the latest model, VocaList, on the LRS2 dataset, achieving a lip-sync detection accuracy of 94.5% based on five context frames. Moreover, our approach exhibits an approximately 8% superiority over VocaList in lip-sync detection accuracy, even on an untrained dataset, Acappella.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.37 no.3
• /
• pp.261-273
• /
• 2024

This paper is an experimental study on the improvement of smoke and flame detection from different materials with YOLO. For the study, images of fires occurring in various materials were collected through an open dataset, and experiments were conducted by changing the main factors affecting the performance of the fire object detection model, such as the bounding box, polygon, and data augmentation of the collected image open dataset during data preprocessing. To evaluate the model performance, we calculated the values of precision, recall, F1Score, mAP, and FPS for each condition, and compared the performance of each model based on these values. We also analyzed the changes in model performance due to the data preprocessing method to derive the conditions that have the greatest impact on improving the performance of the fire object detection model. The experimental results showed that for the fire object detection model using the YOLOv5s6.0 model, data augmentation that can change the color of the flame, such as saturation, brightness, and exposure, is most effective in improving the performance of the fire object detection model. The real-time fire object detection model developed in this study can be applied to equipment such as existing CCTV, and it is believed that it can contribute to minimizing fire damage by enabling early detection of fires occurring in various materials.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.2
• /
• pp.113-120
• /
• 2024

The population sparseness index(PSI) is being utilized to describe the functioning of internal layers in artificial neural networks from the perspective of neurons, shedding light on the black-box nature of the network's internal operations. There is research indicating a positive correlation between the PSI and performance in each layer of convolutional neural network models for image classification. In this study, we observed the internal operations of a convolutional neural network when adversarial examples were applied. The results of the experiments revealed a similar pattern of positive correlation for adversarial examples, which were modified to maintain 5% accuracy compared to applying benign data. Thus, while there may be differences in each adversarial attack, the observed PSI for adversarial examples demonstrated consistent positive correlations with benign data across layers.

• Food Science of Animal Resources
• /
• v.44 no.1
• /
• pp.132-145
• /
• 2024

Sarcopenia, the age-related muscle atrophy, is a serious concern as it is associated with frailty, reduced physical functions, and increased mortality risk. Protein supplementation is essential for preserving muscle mass, and horse meat can be an excellent source of proteins. Since sarcopenia occurs under conditions of oxidative stress, this study aimed to investigate the potential anti-muscle atrophy effect of horse meat hydrolysate using C2C12 cells. A horse meat hydrolysate less than 3 kDa (A4<3kDa) significantly increased the viability of C2C12 myoblasts against H₂O₂-induced cytotoxicity. Exposure of C2C12 myoblasts to lipopolysaccharide led to an elevation of cellular reactive oxygen species levels and mRNA expression of proinflammatory cytokines, including tumor necrosis factor-α and interleukin 6, and these effects were attenuated by A4<3kDa treatment. Additionally, A4<3kDa activated protein synthesis-related proteins through the protein kinase B/mechanistic target of rapamycin pathway, while decreasing the expression of activity and degradation-related proteins, such as Forkhead box O3, muscle RING finger protein-1, and Atrogin-1 in dexamethasone-treated C2C12 myotubes. Therefore, the natural material A4<3kDa has the potential of protecting against muscle atrophy, while further in vivo study is needed.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.1
• /
• pp.195-209
• /
• 2024

The current road traffic signal controller developed in the 1990s has limitations in flexibility and scalability due to power supply problems, various communication methods, and hierarchical black box structures for various equipment and devices installed to improve traffic safety for road users and autonomous cooperative driving. In this paper, we designed a road traffic safety facilities equipment and devices integrated management system that can cope with the rapidly changing future traffic environment by solving the using direct current(DC) and power supply problem through the power over ethernet(PoE) technology and centralized data-driven control through message broker technology. In addition, a data-driven real-time control method for road traffic safety facilities equipment and devices operating based on time series data was implemented and verified.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.1
• /
• pp.67-75
• /
• 2024

Crosswalks play an important role for the safe movement of pedestrians in a complex urban environment. However, for the visually impaired, crosswalks can be a big risk factor. Although assistive tools such as braille blocks and acoustic traffic lights exist for safe walking, poor management can sometimes act as a hindrance to safety. This paper proposes a method to improve accuracy in a deep learning-based real-time crosswalk detection model that can be used in applications for pedestrian assistance for the disabled at the beginning. The image was binarized by utilizing the characteristic that the white line of the crosswalk image contrasts with the road surface, and through this, the crosswalk could be better recognized and the location of the crosswalk could be more accurately identified by using two models that learned the whole and the middle part of the crosswalk, respectively. In addition, it was intended to increase accuracy by creating a boundary box that recognizes crosswalks in two stages: whole and part. Through this method, additional frames that the detection model did not detect in RGB image learning from the crosswalk image could be detected.

• Journal of the Korean Society of Radiology
• /
• v.18 no.1
• /
• pp.21-26
• /
• 2024

The one of the famous deep learning models for object detection task is you only look once version 5 (YOLOv5) framework based on the one stage architecture. In addition, YOLOv5 model indicated high performance for accurate lesion detection using the bottleneck CSP layer and skip connection function. The purpose of this study was to evaluate the performance of YOLOv5 framework according to various hyperparameters in position emission tomogrpahy (PET) phantom images. The dataset was obtained from QIN PET segmentation challenge in 500 slices. We set the bounding box to generate ground truth dataset using labelImg software. The hyperparameters for network train were applied by changing optimization function (SDG, Adam, and AdamW), activation function (SiLU, LeakyRelu, Mish, and Hardwish), and YOLOv5 model size (nano, small, large, and xlarge). The intersection over union (IOU) method was used for performance evaluation. As a results, the condition of outstanding performance is to apply AdamW, Hardwish, and nano size for optimization function, activation function and model version, respectively. In conclusion, we confirmed the usefulness of YOLOv5 network for object detection performance in nuclear medicine images.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.57 no.1
• /
• pp.32-40
• /
• 2024

The aim of this research was to apply a method designed to derive the factors influencing total ammonia removal when operating an additional pretreatment system at Aquaponics. The Box-Behnken method, among response surface analysis methods was used to characterize and determine the optimal nitrification conditions when operating the pretreatment system. Among the mathematically and statistically calculated prediction equations, the total ammonia nitrogen concentration Y1 measured on day 8 was derived as Y₁=-195.8+2.23X₁+42.9X₂+47.5X₃+0.1856X₁²-1.380X₁X₂-1.770X₁X₃, and the time taken to reach the maximum total ammonia nitrogen concentration during the experiment period was derived as Y₂=271-5.04X₁+60.5X₂-64.8X₃+0.1654X₁²+6.54X₃²-0.600X₁X₃-9.00X₂X₃. The coefficients of determination of the regression models of Y₁ and Y₂ were 93.99% and 94.46%, respectively. The modified coefficients of determination were also high, at 89.48% and 88.91%, respectively. The prediction coefficients of determination of Y₁ and Y₂, were 70.68% and 62.11%, respectively, which was relatively lower than that of Y1, but still indicated a reliable prediction performance.

• IMMUNE NETWORK
• /
• v.23 no.3
• /
• pp.25.1-25.17
• /
• 2023

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection induces excessive pro-inflammatory cytokine release and cell death, leading to organ damage and mortality. High-mobility group box 1 (HMGB1) is one of the damage-associated molecular patterns that can be secreted by pro-inflammatory stimuli, including viral infections, and its excessive secretion levels are related to a variety of inflammatory diseases. Here, the aim of the study was to show that SARS-CoV-2 infection induced HMGB1 secretion via active and passive release. Active HMGB1 secretion was mediated by post-translational modifications, such as acetylation, phosphorylation, and oxidation in HEK293E/ACE2-C-GFP and Calu-3 cells during SARS-CoV-2 infection. Passive release of HMGB1 has been linked to various types of cell death; however, we demonstrated for the first time that PANoptosis, which integrates other cell death pathways, including pyroptosis, apoptosis, and necroptosis, is related to passive HMGB1 release during SARS-CoV-2 infection. In addition, cytoplasmic translocation and extracellular secretion or release of HMGB1 were confirmed via immunohistochemistry and immunofluorescence in the lung tissues of humans and angiotensin-converting enzyme 2-overexpressing mice infected with SARS-CoV-2.