Computer Networks & Systems Research Lab
Research Field
Professor Yu-Kuen Lai (Senior Member, IEEE) is currently a Professor with the Electrical Engineering Department, Chung Yuan Christian University (CYCU), Chung-li, Taiwan. He is also the Director of Interdisciplinary Program of Electrical and Computer Engineering and UWM Dual Degree Program of Electrical and Computer Engineering.
Professor Lai received the M.S. and Ph.D. degrees in electrical and computer engineering from North Carolina State University, Raleigh, NC, USA, in 1997 and 2006, respectively. From 1997 to 2002, he was a Senior ASIC Design Engineer with Delta Networks, Inc., and Applied Micro Circuit Corporation (AMCC) in Research Triangle Park, North Carolina, USA. His research interests include software-defined networking, streaming data processing, network traffic analysis, FPGA systems design, and computer network security. Professor Lai served as the Electronic Communication Officer for the IEEE Taipei Section, in 2015. He was a recipient of the CYCU Distinguished Teaching Award, in 2011, and the CYCU Outstanding Teaching Award, in 2017. He was the director of the Information Technology Division, C.Y. Chang Memorial Library from 2018 to 2023. He also received the CYCU Invention Award in 2024 and CYCU Excellence Award of Academia and Industry Collaboration in 2021 and 2023, respectively.
Computer Networks & Systems Research Lab
High-Speed Packet Processing & Measurement
Traffic analysis and measurement are important tasks for the proper operation of IP networks. The accurate estimation of Internet traffic statistics serves as the basis for infrastructure planning, network provisioning, capacity forecasting and accounting. Anomaly detection on worm distribution and prevention of distributed denial of service (DDoS) attacks are also based on the same information. However, as network bandwidth grows exponentially, the scaling of monitoring and measuring capabilities for collecting accurate statistics becomes a critical issue. Hash-based algorithms are very useful and popular techniques adopted in many high-speed router design. We are exploring these advanced techniques with hardware and architecture support for data reduction and synopsis construction.
Packet Processing on Stream Architecture
Stream processing architectures have been proposed as efficient and flexible platforms for network packet processing. This is because packet processing shares many of the same characteristics of media and image processing that motivate stream architectures: little global data reuse, abundant data parallelism, and high computational complexity. Moreover, in comparison with multi-thread approach, stream architecture provides much lower cost to hide a given amount of latency.
Identification of DDoS Attacks Through SHAP-Based Feature Analysis and Transformer Models: A Multivariate Time Series Data Approach.
Real-Time Frequency Moment Estimation on FPGA: Applications in Anomaly Detection and Weibull Flow Length Parameterization.
Sketch-based Entropy Estimation: a Tabular Interpolation Approach Using P4
A Machine Learning Accelerator for DDoS Attack Detection and Classification on FPGA
Prof. Lai was a recipient of the CYCU Distinguished Teaching Award, in 2011, and the CYCU Outstanding Teaching Award, in 2017. He also received the CYCU Invention Award in 2024 and CYCU Excellence Award of Academia and Industry Collaboration in 2021 and 2023, respectively.
2024 iENA, International Invention Exhibition in Nuremberg, Germany, "Best International Invention and Innovation" Special Award
2023 iENA, International Invention Exhibition in Nuremberg, Germany, Gold Medal Award
2023 Taiwan Innovation Technology Expo, Invention Competition, Silver Medal Award
Professor Lai received the M.S. and Ph.D. degrees in electrical and computer engineering from North Carolina State University, Raleigh, NC, USA, in 1997 and 2006, respectively.
1 Vacancy
Job Description
- Develop and implement network functions on Intel Tofino Switch using P4 language.
- Optimize packet processing and flow control for anomaly detection at the data plane level.
- Integrate C/Python-based control plane applications with P4-implemented functions.
- Conduct performance evaluations and benchmarking of network functions on Intel Tofino.
- Work with network traffic and protocol analysis to detect anomalies in real-time.
- Research and develop security mechanisms using programmable data planes.
- Document implementation processes, findings, and performance metrics.
Preferred Intern Education Level
Students in the Master degree program
Skill sets or Qualities
- Hands-on experience with P4 programming and programmable switches (Intel Tofino preferred).
- Proficiency in C and Python for network function development and automation.
- Strong understanding of computer network architecture, including protocol stack (TCP/IP, Ethernet, BGP, etc.).
- Knowledge of network security principles and common security threats.
- Familiarity with SDN concepts, data plane programmability, and control plane integration.
- Experience with network traffic analysis tools (e.g., Wireshark, tcpdump, Scapy).
- Experience with P4 development environments (BMv2, Tofino P4 Studio, P4Runtime).
1 Vacancy
Job Description
- Analyze large-scale network traffic and flow data to identify anomalies and suspicious patterns.
- Implement and test anomaly detection algorithms using artificial neural networks (ANN) and statistical models.
- Develop Python/C-based tools for processing and analyzing network traffic.
- Utilize machine learning frameworks (such as TensorFlow, PyTorch) to build and train models for anomaly detection.
- Apply statistical methods to improve detection accuracy and reduce false positives.
- Work with network security data and assist in refining detection techniques.
- Document findings, methodologies, and experimental results for internal review.
Preferred Intern Education Level
Graduate students in the Master degree program
Skill sets or Qualities
- Strong programming skills in C and Python.
- Familiarity with artificial neural networks (ANN) and machine learning frameworks (e.g., TensorFlow, PyTorch, Scikit-learn).
- Experience with statistical analysis tools (e.g., R, MATLAB, NumPy, Pandas).
- Knowledge of network traffic analysis and common networking protocols (TCP/IP, HTTP, DNS, etc.).
- Basic understanding of anomaly detection techniques and their applications in cybersecurity.
- Ability to work with large datasets and conduct meaningful data analysis.
- Strong problem-solving skills and attention to detail.
- Experience with packet analysis tools (e.g., Wireshark, Zeek).
- Understanding of time-series analysis for detecting network anomalies.
- Familiarity with cybersecurity concepts and threat detection techniques.
- Knowledge of distributed computing and cloud-based analytics.