A privacy preserving dashboard that shows educational institutions how their internet is used, by classifying encrypted network traffic by application without reading any content.
This work presents a lightweight method that detects malicious encrypted network traffic from the first few packets of a connection. It uses only packet timing and size patterns, with no decryption, and reaches high accuracy with low false alarm rates on three types of attack traffic.
Smartphone-based soil analysis and crop-planning intelligence
Developing an accessible system that estimates soil properties from smartphone images and combines them with climate and geospatial data to support Bangladeshi farmers.
An AI-assisted legal services platform for client intake, research, drafting, and case management — with licensed lawyer oversight and Bangla–English support.
An AI system for early disease screening from non-invasive signals — medical images, voice, cough, vitals, and wearables — with physician oversight and low-cost community access.