Researchers develop privacy-preserving cameras for smart home devices

From robotic vacuum cleaners to baby monitors, the smart devices which are becoming increasingly present in homes and workplaces use images and videos to navigate and monitor their surroundings.  

These devices form part of the internet-of-things (IoT), smart systems that connect to the internet to operate. As such, they can be at risk of being hacked or lost through human error, making the images and data they collect vulnerable to theft by third parties, sometimes with malicious intent.

To counter this, researchers from the Australian Centre for Robotics at the University of Sydney and the QUT Centre for Robotics (QCR) at Queensland University of Technology have created a new approach to designing cameras that process and scramble visual information before it is digitised so that it becomes obscured to the point of anonymity. 

Researchers said the distorted images can still be used by robots to complete their tasks but do not provide a comprehensive visual representation that compromises privacy. 

In a statement, Adam Taras, who completed the research as part of his Honours thesis at the University of Sydney, said: “Smart devices are changing the way we work and live our lives, but they shouldn’t compromise our privacy and become surveillance tools. 

“When we think of ‘vision’ we think of it like a photograph, whereas many of these devices don’t require the same type of visual access to a scene as humans do. They have a very narrow scope in terms of what they need to measure to complete a task, using other visual signals, such as colour and pattern recognition.” 

The research team were able to segment the processing that normally happens inside a computer within the optics and analogue electronics of the camera, which exists ‘beyond the reach of attackers.’ 

The researchers said they tried to hack their approach but were unable to reconstruct the images in any recognisable format. They have opened this task to the research community, challenging others to hack their method. 

“If these images were to be accessed by a third party, they would not be able to make much of them, and privacy would be preserved,” said Taras. 

Dr Don Dansereau, Taras’ supervisor at the Australian Centre for Robotics and Digital Sciences Initiative, said privacy was increasingly becoming a concern as more devices come with built-in cameras, and with the possible increase in new technologies like parcel drones, which would make deliveries in residential areas.   

“You wouldn’t want images taken inside your home by your robot vacuum cleaner leaked on the dark web, nor would you want a delivery drone to map out your backyard. It is too risky to allow services linked to the web to capture and hold onto this information,” he said. 

The researchers said this new technology could be used in devices that work in places where privacy and security are a concern, such as warehouses, hospitals, factories, schools and airports. 

Looking ahead, the researchers said they are aiming to build physical camera prototypes to demonstrate the approach in practice.   

The research, published in the Journal of Responsible Technology, can be read in full here.