Welcome!
The Programmable and Intelligent Networking (PINet) Lab is a research lab in the Faculty of Computer Science
at Dalhousie University. Prof. Israat Haque leads the lab.
The current projects of the lab span network performance, reliability, and security aspects. We explore the
benefits of cutting-edge networking programmability (e.g., software-defined networking and network function
virtualization) and
AI/ML algorithms to solve various practical networking problems, where our focus goes to wired and wireless
networks, e.g., WAN, data centers, Edge, and IoT.
We desire to innovate and create social impact through high-quality work. PINET lab currently has over ten
graduate and undergraduate students. We commit to foster diversity and always welcome highly
motivated top students from
all over the world.
The lab offers courses on Software-Defined Networking, Information Security, and Network Computing at least
once a year.
Latest news
- Mar 2024: Our proposal "Multi-disciplinary Approach to Research, Education, and Training in Cybersecurity for Emerging Technologies" received the NSERC CREATE grant.
- Mar 2024: Dr. Haque received the Discovery Grant for "FarmPro: programmable and intelligent edge-cloud systems for smart farming".
- Mar 2024: Our proposal "Mitigating Security Threats in Industrial Cyber Physical Systems using Autonomous Agents" received the FQRNT-NSERC grant.
- Dec 2023: Monzurul has been selected for the Upper Bound Talent Bursary to join the 2024 Upper Bound AI Conference in Edmonton.
- Sept 2023: Dr. Haque will give a keynote at IEEE Workshop on Machine Intelligence in Networked Data and Systems (MINDS) in January 2024.
- June 2023: "Preventing Discriminatory Decision-Making in Evolving Data Streams" received the best paper award at ACM Conference on Fairness, Accountability, and Transparency (FAccT).
Recent publications
- P4Hauler: an Accelerator-aware In-network Load Balancer for Applications Performance Boosting, accepted at IEEE Transactions on Cloud Computing 2024. [Paper]
- Calibration and Automation of a 5G Simulator for Realistic Evaluation and Data Generation, accepted at IEEE International Conference on Network Softwarization 2024. [Paper]
- PoirIoT: Fingerprinting IoT Devices at Tbps Scale, accepted at IEEE/ACM Transactions on Networking 2024.
- Learn to Compress (LtC): Efficient Learning-based Streaming Video Analytics, IEEE/IFIP NOMS 2024. [Paper]
- On the (dis)Advantages of Programmable NICs for Network Security Services, IEEE/IFIP Networking Conference 2023. [Paper]
- Offloading Machine Learning to Programmable Data Planes: A Systematic Survey, ACM Computing Surveys 2023. [Paper]
- Fast Prototyping of Distributed Stream Processing Applications with stream2gym, IEEE ICDCS 2023. [Paper]
- A Deep Neural Network-based Communication Failure Prediction Scheme in 5G RAN, IEEE TNSM 2022. [Paper]
- NetGVT: Offloading Global Virtual Time Computation to Programmable Switches, ACM SOSR 2022. [Paper]
- BlueTiSCH: A Multi-PHY Simulation of Low-Power 6TiSCH IoT Networks, IEEE Globecom 2022. [Paper]
- Towards Portable End-to-End Network Performance Characterization of SmartNICs, ACM APSys 2022. [Paper]
- Accelerator-Aware In-Network Load Balancing for Improved Application Performance, IEEE/IFIP Networking 2022. [Paper]
- IoT Device Fingerprinting on Commodity Switches, IEEE/IFIP NOMS 2022. [Paper]