Mirai Lab research
CASTLE: Content And Security Traffic Lens for Educational Institutes
A privacy preserving dashboard that shows educational institutions how their internet is used, by classifying encrypted network traffic by application without reading any content.
- Network Traffic Analysis
- Encrypted Traffic Classification
- Machine Learning
- Deep Learning
- Time Series Classification
A privacy preserving dashboard that shows educational institutions how their internet is used, by classifying encrypted network traffic by application without reading any content.
Research approach
- Step 1
Define
Frame the problem, requirements, and evaluation criteria for the research initiative.
- Step 2
Build
Develop models, systems, and experiments aligned with the project objectives.
- Step 3
Validate
Evaluate outcomes through pilots, benchmarks, or field studies before wider deployment.
Overview
Most internet traffic is now encrypted, so educational institutions can no longer see what their network is being used for. CASTLE restores this visibility using only the visible “envelope” of each packet (size, direction and timing), never the content.
An early-classification model (an LSTM) identifies the application behind each traffic flow, such as Zoom, the LMS or YouTube, from only its first few packets. It labels unfamiliar traffic as “unknown” instead of guessing. The results feed an interactive dashboard that shows usage by application, educational category (learning, research, communication, social media, video), time of day and institute. This helps institutions and network operators plan capacity, support online learning, and notice unusual traffic patterns.
The system is being built and tested on public datasets and, with support from BdREN, will be evaluated on real Bangladeshi educational traffic. IP addresses are anonymised and results are reported only in aggregate.
Team
Project lead: Sanjana Islam
Collaborators: BdREN
Publications and datasets
Research papers, models, and open datasets will be shared here as they are released.
Project updates
Milestones, fieldwork notes, and lab announcements will appear on our notices page.
View notices →