Imagine a distopian world in which privacy did not exist and Big Brother was able to monitor everything you wrote down, even if you made sure there were no cameras behind you.
Imagine the development of automatic surveillance systems able to pull data from your eyes.
This is not the future. This is now (sort of).
Researchers have investigated the possibility of capturing reflections of mobile device screens onto video and then using the footage to reconstruct typed words and phrases automatically.
For example, they used consumer video cameras to capture the reflections cast by a smartphone onto the surface of the user's spectacles. The video footage was then analysed and the text extracted.
In their paper, iSpy: Automatic Reconstruction of Typed Input from Compromising Reflections, Rahul Raguram, Andrew M. White, Dibenyendu Goswami, Fabian Monrose and Jan-Michael Frahm wrote:
"Despite our deliberate use of low cost commodity video cameras, we are able to compensate for variables such as arbitrary camera and device positioning and motion through the application of advanced computer vision and machine learning techniques.
Using footage captured in realistic environments (e.g., on a bus), we show that we are able to reconstruct fluent translations of recorded data in almost all of the test cases, correcting users' typing mistakes at the same time."The video below, from a page containing some other related videos, shows how this interesting and somewhat sinister work plays out in practice.
No comments:
Post a Comment