A team of researchers found that conventional robotic vacuum cleaners can be hacked and used as a microphone. The research team led by Nirupam Roy, assistant professor of computer science at the University of Maryland, in collaboration with associate professor at the University of Singapore, Jun Han, used information from a laser navigation system that was processed using deep learning technology to reproduce conversations in the room where the device was operating.
The researchers argue that any robot vacuum cleaner that uses distance sensors can transmit sound, even if they don’t have a microphone. The research findings were presented at the Computing Machinery Association’s Embedded Networked Sensor Systems Conference (SenSys 2020) last month.
The navigation systems in robotic vacuums emit a laser beam, the reflected signals used to create a map of the room, allowing the robot to move around the room without collisions. In most cases, these cards are stored in the cloud and are believed to pose a potential security and privacy threat and could present an attacker with unauthorized access to users’ personal data.
By breaking into a vacuum cleaner, hackers can obtain accurate information about the room’s size and record conversations in users’ homes or businesses.