IIT Delhi study reveals GPS data can infer activity and room layout
IIT Delhi researchers published a study demonstrating that fine-grained GPS data accessible to Android apps with standard location permissions can infer detailed information about user activities, surroundings, and indoor room layouts without explicit consent, exposing a security gap in mobile app permissions.
What happened
IIT Delhi researchers developed AndroCon, a system that uses fine-grained GPS data already accessible to Android apps with precise location permissions to infer sensitive contextual information without explicit user consent.
The system interprets nine low-level GPS parameters including Doppler shift, signal power, and multipath interference to determine whether someone is sitting, standing, or lying down, their location type (metro, flight, park, crowded space), and whether a room is crowded or empty.
The framework can also sketch indoor floor maps identifying rooms, staircases, and elevators with a margin of error under 4 metres using only GPS patterns and user trajectories.
Reported impact
The study exposes a critical security gap in Android permissions. Any Android app with precise location permissions could potentially infer sensitive contextual information about users without their explicit consent.
Index analysis
AndroCon achieved up to 99 per cent accuracy in detecting surroundings and over 87 per cent accuracy in recognising human activities across a year-long study spanning 40,000 square kilometres and multiple phone devices.
Classification
Sources and evidence
Sources not yet published
This record was researched and written by the Index from original reporting. Its sources are still being verified by an editor, and they are listed here once that check is complete. Until then the record carries no reviewer.