A5030514608- Internet Traffic Analysis and Secure E-voting
- Topic Modeling
- Network Security and Intrusion Detection
- Advanced Graph Neural Networks
- Anomaly Detection Techniques and Applications
- Kidney Stones and Urolithiasis Treatments
- Parathyroid Disorders and Treatments
- Renal cell carcinoma treatment
- Semantic Web and Ontologies
- Network Packet Processing and Optimization
- Machine Learning in Healthcare
- Epilepsy research and treatment
- Data Quality and Management
- Network Traffic and Congestion Control
- Natural Language Processing Techniques
Sun Yat-sen University
2024
Hunan University
2018-2020
Low-rate denial of service (LDoS) attacks reduce the quality network by sending periodical packet bursts to bottleneck routers. It is difficult detect counter-DoS mechanisms due its stealthy and low average attack traffic behavior. In this paper, we propose an anomaly detection method based on adaptive fusion multiple features (MAF-ADM) for LDoS attacks. This study fact that time-frequency joint distribution legitimate transmission control protocol (TCP) would be changed under Several...
To date, Denial of Service (DoS) attack still causes great damage to the Internet in spite many years' research on its detection and defense. Low-rate (LDoS) attack, a new type DoS exploits congestion control mechanism Transmission Control Protocol (TCP) degrade throughput network by sending periodic pulse traffic. The applied LDoS makes average traffic speed very low compared which means existing methods based high are incapable detecting attack. In this paper, we propose correlation-based...
Knowledge graph completion (KGC) aims to identify missing triples in a knowledge (KG). This is typically achieved through tasks such as link prediction and instance completion. However, these methods often focus on either static graphs (SKGs) or temporal (TKGs), addressing only within-scope triples. paper introduces new generative framework called Generative Subgraph-based KGC (GS-KGC). GS-KGC employs question-answering format directly generate target entities, the challenge of questions...