A5028129292- Cloud Computing and Resource Management
- Network Security and Intrusion Detection
- Advanced Malware Detection Techniques
- Internet Traffic Analysis and Secure E-voting
- Software System Performance and Reliability
- Software-Defined Networks and 5G
- IPv6, Mobility, Handover, Networks, Security
- Scientific Computing and Data Management
- Cryptography and Data Security
- Distributed and Parallel Computing Systems
- Anomaly Detection Techniques and Applications
- Data Stream Mining Techniques
- Big Data and Business Intelligence
- Advanced Data Storage Technologies
- Privacy-Preserving Technologies in Data
- Mobile Agent-Based Network Management
- Caching and Content Delivery
- Distributed systems and fault tolerance
- Information and Cyber Security
- Stochastic Gradient Optimization Techniques
Chungnam National University
2022
Jingdong (China)
2018-2019
Louisiana State University
2017-2019
Silicon Valley Community Foundation
2019
MACOM (United States)
2018
Louisiana State University Agricultural Center
2017
Microservice architectures and container technologies are broadly adopted by giant internet companies to support their web services, which typically have a strict service-level objective (SLO), tail latency, rather than average latency. However, diagnosing SLO violations, e.g., long latency problem, is non-trivial for large-scale applications in shared microservice platforms due million-level operational data complex environments.
As the extension of Distributed Denial-of-Service (DDoS) attacks to application layer in recent years, researchers pay much interest these new variants due a low-volume and intermittent pattern with higher level stealthiness, invaliding state-of-the-art DDoS detection/defense mechanisms. We describe type attack--Tail Attacks on Web Applications. Such attack exploits newly identified system vulnerability n-tier web applications (millibottlenecks sub-second duration resource contention strong...
The increasingly popular fused batch-streaming big data framework, Apache Flink, has many performance-critical as well untamed configuration parameters. However, how to tune them for optimal performance not yet been explored. Machine learning (ML) chosen the configurations other frameworks (e.g., Spark), showing significant improvements. it needs a long time collect large amount of training by nature. In this article, we propose guided machine (GML) approach Flink with significantly shorter...
In this paper, we present Fedlearn-Algo, an open-source privacy preserving machine learning platform. We use platform to demonstrate our research and development results on algorithms. As the first batch of novel FL algorithm examples, release vertical federated kernel binary classification model random forest model. They have been tested be more efficient than existing models in practice. Besides also a communication module. The uniform data transfer interface supports transferring widely...
Fast response time becomes increasingly important for modern web applications (e.g., e-commerce) due to intense competitive pressure. In this paper, we present a new type of Denial Service (DoS) Attacks in the cloud, MemCA, with goal causing performance uncertainty (the long-tail problem) target n-tier application while keeping stealthy. MemCA exploits sharing nature public cloud computing platforms by co-locating adversary VMs that host application, and intermittent short-lived...
Containers and microservices are dominating the world of data center cloud computing. As scale, dynamism complexity grow, performance DNS system in container clusters becomes vital. world's third China's largest e-commerce site by revenue, JD.com runs one Kubernetes production. It is imperative that can handle extremely high traffic. In this paper, we present ContainerDNS, a for very large scale with millions containers. ContainerDNS maximizes scalability optimizing packet processing using...
Asynchronous event-driven server architecture has been considered as a superior alternative to the thread-based counterpart due reduced multithreading overhead. In this paper, we conduct empirical research on efficiency of asynchronous Internet servers, showing that an may perform significantly worse than one two design deficiencies. The first is widely adopted one-event-one-handler event processing model in current which could generate frequent unnecessary context switches between handlers,...