Swiss researchers have developed a new Android application that enables securing shared information automatically.
The app, said to be the first semi-automated system to filter what information from a smartphone can be transmitted to a third party or made accessible, will undergo an extensive trial during the summer to validate the approach.
Developed by Igor Bilogrevic and Kevin Huguenin, both researchers at the Laboratory for Computer Communications and Applications at the Swiss Federal Institute of Technology in Lausanne (EPFL), is designed to protect data such as geographical location or current activities that could be exploited by cyber criminals.
Until now, smartphone users have had to manually set all safety parameters, for example, when accepting a new friend on Facebook. The researchers believe the new app, once past the initial machine learning stages, would take this burden off the users’ shoulders and independently decide which information should be shared and transmitted.
During use, the intelligent software learns the criteria – the time of day, location, or relationship to the person or application seeking access to information – that could influence the decision of the user. It assimilates information with software that recognizes voice or writing, in order to make the decision automatically. It can also be driven in a fun way by making a targeted ping-pong of questions and answers called active learning or by correcting incorrect decisions made by the software.
The first phase of evaluation, based on situational questionnaires, just finished with the help of a panel of experienced users. It included questions about the habits of people who use social networks and the effectiveness of active learning. The evaluation demonstrated that the automated system was between 80 and 90 per cent reliable.