Scientists Hacked Vacuum Cleaners To Make A Spying Device

Could your vacuum cleaners be listening to you? A team of scientists demonstrated that vacuum cleaners could be hacked to act as microphones, according to Techxplore.

The work was primarily led by the National University of Singapore by which Nirupam Roy, an assistant professor in the Department of Computer Science at the University of Maryland, collaborated with to collect data from the laser-based navigation system of robotic vacuum cleaners and applied signal processing and deep learning techniques to retrieve the speech and TV programs that are being played in the same room where the device was.

Their research shows that any device that uses Light Detection and Ranging (Lidar) technology can be hacked for collecting sound even if these robotic devices do not have microphones.

Roy noted that these robotic vacuum cleaners, being used at homes, can be used for navigation to spy on conversations that could reveal private conversations if it is hacked even though it does not have microphones.

How Does Lidar Technology in Vacuum Cleaners Work?

Lidar technology is a remote sensing method that uses a pulsed laser to measure ranges at variable distances on Earth. These laser pulses generate precise and 3D information about the shape of the Earth. It mainly consists of a scanner, laser, and specialized GPS.

In robot vacuum cleaners the Lidar technology shines a light beam around the room and senses the reflection of the laser bounces in the nearby objects which is used by the robot to map the room and avoid colliding to objects as it moves through while cleaning the house.

The maps are stored in the cloud in which experts said this information could be used to breach the privacy of the household. It could give advertisers access to information that should have remained private. Roy and his team also said that these robot vacuum cleaners pose security risks as sound recorders in businesses or homes.

A vacuum Lidar scans the environment with a pulsed laser and senses light scattered back that are irregular in density and shape. The sensor receives the light that consists of a fraction of the information needed to retrieve the sound waves it recorded.

The researchers said that they tried manipulating the vacuum cleaners to function as microphones and see if they could interpret sound waves into meaningful signals.

Vacuum Cleaners As Microphones

The researchers hacked the robot vacuum to control the laser beam and send the data to their computers via Wi-Fi without interfering with the navigation of the vacuum.

They then conducted experiments on two sound sources: human voice reciting numbers played over computer speakers, and audio from various shows played on the TV. Then they captured the laser signal sensed by the vacuum cleaner as it bounced off in some objects present on the floor, such as trash can, cardboard box, and takeout container.

The researchers passed the received signals through deep learning algorithms, which they call the LidarPhone, to identify and match the sounds. They found that it matched 90% with the spoken numbers as well as more than 90% accuracy in the sounds from the television shows.

"This type of threat may be more important now than ever when you consider that we are all ordering food over the phone and having meetings over the computer, and we are often speaking our credit card or bank information," Roy said.

They emphasized that vacuum cleaners are just one of the many common technologies that pose a potential risk of being spied on by other people, such as smartphones, according to iNews.