- Network Security and Intrusion Detection
- Cloud Computing and Resource Management
- Advanced Malware Detection Techniques
- IoT and Edge/Fog Computing
- Digital and Cyber Forensics
- Software System Performance and Reliability
- Distributed and Parallel Computing Systems
- Anomaly Detection Techniques and Applications
- Digital Transformation in Industry
- Parallel Computing and Optimization Techniques
- Information and Cyber Security
- Traffic Prediction and Management Techniques
Dongguk University
2019-2024
Internet of Things (IoT) technology provides the basic infrastructure for a hyper connected society where all things are and exchange information through Internet. IoT is fused with 5G artificial intelligence (AI) technologies use various fields such as smart city factory. As demand increases, security threats against infrastructure, applications, devices have also increased. A variety studies been conducted on detection malware to avoid posed by malicious code. While existing models may...
With the steady increase in demand for Internet of Things (IoT) devices diverse industries, such as manufacturing, medical care, and transportation infrastructure, production malware tailored Smart IoT environments is also increasing. Accordingly, various detection studies are being conducted to detect not only known but variant malware. However, it difficult transformed a way that hides malicious behavior by changing deleting bytes or modifying assembly code. Therefore, this study, we...
In this article, we propose the hybrid malware detection scheme, HyMalD, with bidirectional long short-term memory (Bi-LSTM) and spatial pyramid pooling network (SPP-Net). Its purpose is to protect Internet of Things (IoT) devices minimize damage caused by infection through obfuscated malware. HyMalD performs static dynamic analyses logically simultaneously detect malware, which impossible do using analysis alone. First, it extracts features opcode sequence a reconstructed dataset according...
The container resource autoscaling technique provides scalability to cloud services composed of microservice architecture in a cloud-native computing environment. However, the service efficiency is reduced as scaling delayed because dynamic loads occur with various workload patterns. Furthermore, estimating efficient size for difficult, resulting waste and overload. Therefore, this study proposes high-performance management (HiPerRM), which stably elastically manages resources ensure even...
The healthcare industry is collecting considerable patient and medical data by using Internet of Things (IoT) devices. Consequently, ransomware attacks to encrypt systems or leak such have increased recently. Many studies are aiming predict behaviours early protect the IoT environment from attacks. However, previous analysed for long periods time, would already get infected encrypted meanwhile. To avoid this problem, study proposes an prediction scheme behaviour (EPS-Ran) reduce likelihood...
With the advent of Industry 4.0, high-quality consumer electronics are being efficiently produced by simulating a virtual model connected to physical object using digital twin (DT) technology. Furthermore, high-performance cloud computing technology is used simulate resource-intensive DT. Virtual machine (VM)-based DT simulation can various DTs in parallel, but VM heavy due hypervisor and has slow startup time. In contrast, container-based lightweight fast-driving elastically utilize...
In a cloud computing environment, the container scheduling technique ensures reliability for containerized applications by selecting nodes that satisfy various resource requirements and then deploying containers. If initial resources of are over-allocated, may be wasted, or other containers waiting in queue not allocated. However, if under-allocated, service disruptions occur due to node overbooking, cannot ensured. Therefore, this study, forecasted resource-evaluating scheduler (FoRES) is...
Abstract As digital transformation accelerates, data generated in a convergence information and communication technology (ICT) environment must be secured. This includes confidential such as personal financial information, so attackers spread malware ICT environments to steal this information. To protect from diverse cyber threats, deep learning models have been utilized for detection. However, accurately detecting rapidly variants obfuscated is challenging. study proposes three‐tier...
Cloud computing services that provide resources to users through the Internet also in a virtual machine form based on virtualization techniques. In general, supercomputing and grid have mainly been used process large-scale jobs occurring scientific, technical, engineering application domains. However, parallel using idle machines are not provided cloud at present. Generally, do use anymore, or they them for long period of time, because existing assigns all rights users, resulting low...