https://scholarworks.korea.ac.kr/kumedicine/handle/2020.sw.kumedicine/660 Sat, 11 Apr 2026 12:43:11 GMT 2026-04-11T12:43:11Z https://scholarworks.korea.ac.kr/kumedicine/handle/2021.sw.kumedicine/79469 Title: Advanced Side-Channel Evaluation Using Contextual Deep Learning-Based Leakage Modeling Authors: Alabdulwahab, Saleh; Kim, Jaecheol; Kim, Young-Tak; Son, Yunsik Abstract: Side-channel attacks (SCAs) exploit power analysis to extract secret information. Researchers have employed this technique to disassemble software and retrieve cryptographic keys by examining power consumption or electromagnetic emissions. They utilized hardware or Hamming-based fluctuations measurement to profile or model the power leakage. Developers employ power modeling to comprehend software leakage, although manually profiling the power trace across various devices and architectures requires time and effort. This work proposes a custom deep learning (DL) method to model the power trace. The DL model was trained to analyze how each assembly instruction produces leakage based on its context with other instructions. The proposed method can predict the power trace with 0.9963 R2 from unseen assembly instructions. This method automates device leakage testing and captures contextual and non-linear relationships to help developers understand the software behavior, significantly reducing the time and effort required for power modeling. The potential impact of this DL model on software security is that it can effectively mitigate the risk of SCAs, thus enhancing the overall security of software systems. Thu, 01 Jan 2026 00:00:00 GMT https://scholarworks.korea.ac.kr/kumedicine/handle/2021.sw.kumedicine/79469 2026-01-01T00:00:00Z https://scholarworks.korea.ac.kr/kumedicine/handle/2021.sw.kumedicine/78679 Title: Cell-derived vesicles extruded from adipose mesenchymal stem cells attenuate intestinal inflammation and augment epithelial regeneration in a colitis model Authors: Jo, Min Kyoung; Jeon, Hyeon-Jeong; Kim, So Hui; Lee, Hye Sun; Kim, Seong-Eun; Jung, Sung-Ae; Lau, Hui-Chong; Park, Sung-Soo; Oh, Seung Wook; Moon, Chang Mo Abstract: Adipose-derived stem cell (ADSC) cell-derived vesicles (CDVs) have been developed to overcome the limitations of ADSCs and ADSC extracellular vesicles (EVs). This study aims to analyze the characteristics and therapeutic effects of ADSC CDVs compared to ADSCs and ADSC EVs through ex vivo organoid and in vivo colitis experiments. ADSC CDVs were generated from ADSCs through serial extrusions using polycarbonate membrane filters. The characteristics and regenerative efficacy of ADSC CDVs were compared to those of ADSC EVs. The therapeutic effect of ADSC CDVs was evaluated by assessing epithelial regeneration and inflammatory cytokines in vitro, utilizing organoid models ex vivo, and using the dextran sodium sulfate (DSS)-induced colitis model in vivo. Both ADSC EVs and ADSC CDVs exhibited circular shapes, but the mean size of ADSC CDVs (164.3 nm) was significantly larger than that of ADSC EVs (134.8 nm). ADSC CDVs showed a stronger effect on proliferation, migration, and wound healing compared to ADSC EVs. Furthermore, ADSC CDVs upregulated the S phase of the cell cycle and the expression of gut regeneration markers, including beta-catenin, OLFM4, and Ki-67. ADSC CDVs increased the formation and growth of colon organoids after IFN-gamma treatment. Additionally, ADSC CDV treatment reduced the elevated levels of inflammatory cytokines in the organoid model. Treatment with ADSC CDVs also attenuated acute inflammation in the DSS-induced colitis model. ADSC CDVs attenuate gut epithelial inflammation and induce epithelial regeneration ex vivo in organoids and in vivo in a mouse model of colitis. Mon, 01 Dec 2025 00:00:00 GMT https://scholarworks.korea.ac.kr/kumedicine/handle/2021.sw.kumedicine/78679 2025-12-01T00:00:00Z https://scholarworks.korea.ac.kr/kumedicine/handle/2021.sw.kumedicine/75780 Title: Enhancing deep learning-based side-channel analysis using feature engineering in a fully simulated IoT system Authors: Alabdulwahab, Saleh; Cheong, Muyoung; Seo, Aria; Kim, Young-Tak; Son, Yunsik Abstract: The increasing integration of cloud and embedded systems has made security more critical. Despite efforts to implement countermeasures against attacks, new threats have constantly emerged. Deep learning (DL) is most notable for side-channel disassembly attacks that expose cloud-to-things operations. This underscores the need to develop effective tools to test a system's robustness against such attacks. In this study, we developed a robust instruction-level side-channel disassembler for hiding countermeasures in a fully simulated embedded system. We investigated the effect of a moving-window-based feature engineering technique using statistical methods on the performance of side-channel disassembly attacks orchestrated via DL models. In addition, we propose a moving log-transformed temporal integration feature that enhances the performance of DL models for detecting and inferencing tasks. The created dataset was applied for two DL tasks: detecting hiding countermeasures and inferring assembly instructions. Using our feature engineering method, we found that the artificial neural network (ANN) showed an accuracy of 98.81% for hiding countermeasure detection, and the gated recurrent unit (GRU) model inferred the assembly sequence with 98.7% accuracy. These results highlight the need for advanced hardware- and software-level security measures to prevent side-channel attacks on embedded devices as potential vulnerabilities in the cloud infrastructure. Sat, 01 Mar 2025 00:00:00 GMT https://scholarworks.korea.ac.kr/kumedicine/handle/2021.sw.kumedicine/75780 2025-03-01T00:00:00Z https://scholarworks.korea.ac.kr/kumedicine/handle/2021.sw.kumedicine/75326 Title: HKA-Net: clinically-adapted deep learning for automated measurement of hip-knee-ankle angle on lower limb radiography for knee osteoarthritis assessment Authors: Kim, Young-Tak; Han, Beom-Su; Kim, Jung Bin; Sa, Jason K.; Hong, Je Hyeong; Son, Yunsik; Han, Jae-Ho; Do, Synho; Chae, Ji Seon; Bae, Jung-Kwon Abstract: Background: Accurate measurement of the hip-knee-ankle (HKA) angle is essential for informed clinical decision-making in the management of knee osteoarthritis (OA). Knee OA is commonly associated with varus deformity, where the alignment of the knee shifts medially, leading to increased stress and deterioration of the medial compartment. The HKA angle, which quantifies this alignment, is a critical indicator of the severity of varus deformity and helps guide treatment strategies, including corrective surgeries. Current manual methods are labor-intensive, time-consuming, and prone to inter-observer variability. Developing an automated model for HKA angle measurement is challenging due to the elaborate process of generating handcrafted anatomical landmarks, which is more labor-intensive than the actual measurement. This study aims to develop a ResNet-based deep learning model that predicts the HKA angle without requiring explicit anatomical landmark annotations and to assess its accuracy and efficiency compared to conventional manual methods. Methods: We developed a deep learning model based on the variants of the ResNet architecture to process lower limb radiographs and predict HKA angles without explicit landmark annotations. The classification performance for the four stages of varus deformity (stage I: 0°–10°, stage II: 10°–20°, stage III: > 20°, others: genu valgum or normal alignment) was also evaluated. The model was trained and validated using a retrospective cohort of 300 knee OA patients (Kellgren-Lawrence grade 3 or higher), with horizontal flip augmentation applied to double the dataset to 600 samples, followed by fivefold cross-validation. An extended temporal validation was conducted on a separate cohort of 50 knee OA patients. The model's accuracy was assessed by calculating the mean absolute error between predicted and actual HKA angles. Additionally, the classification of varus deformity stages was conducted to evaluate the model's ability to provide clinically relevant categorizations. Time efficiency was compared between the automated model and manual measurements performed by an experienced orthopedic surgeon. Results: The ResNet-50 model achieved a bias of − 0.025° with a standard deviation of 1.422° in the retrospective cohort and a bias of − 0.008° with a standard deviation of 1.677° in the temporal validation cohort. Using the ResNet-152 model, it accurately classified the four stages of varus deformity with weighted F1-score of 0.878 and 0.859 in the retrospective and temporal validation cohorts, respectively. The automated model was 126.7 times faster than manual measurements, reducing the total time from 49.8 min to 23.6 sec for the temporal validation cohort. Conclusions: The proposed ResNet-based model provides an efficient and accurate method for measuring HKA angles and classifying varus deformity stages without the need for extensive landmark annotations. Its high accuracy and significant improvement in time efficiency make it a valuable tool for clinical practice, potentially enhancing decision-making and workflow efficiency in the management of knee OA. © The Author(s) 2024. Fri, 01 Nov 2024 00:00:00 GMT https://scholarworks.korea.ac.kr/kumedicine/handle/2021.sw.kumedicine/75326 2024-11-01T00:00:00Z