This site uses cookies to improve your experience and to provide services and advertising. By continuing to browse, you agree to the use of cookies described in our Cookies Policy. You may change your settings at any time but this may impact on the functionality of the site. To learn more see our Cookies Policy.
OK
Dublin: 7 °C Sunday 8 December, 2019
Advertisement

This project by Westmeath students aims to help parents know when a smart toy has been hacked

They were inspired to conduct research in the smart toys after the number of controversies surrounding them in recent years.

IMG_2407 Amy (left) and Andrea (right) working on their device. Source: Athlone Community College

A YOUNG SCIENTIST project by two Westmeath students aims to alert parents to when a smart toy is being hacked.

Amy Fallon and Andrea Whyte from Athlone Community College are developing a device for the BT Young Scientist & Technology Exhibition that will monitor the connection between the device and a smartphone, and flag when activity is out of the ordinary.

They were inspired to conduct research in the smart toys after the number of controversies surrounding them in recent years, such as with the Cayla talking doll last year.

The doll works by sending a child’s audio question wirelessly to an app on a digital device, which translates it into text and searches the internet for an answer, then sends back a response that is voiced by the doll.

Concerns were raised that hackers might be able to access the doll’s microphone, and be able to listen in on children.

The Federal Network Agency in Germany urged any parents who had bought the toy to destroy it, in part due to the country’s laws on surveillance.

Genesis Toys, which manufactures the doll, said on its website that it “is committed to protecting your and your family’s personal information”, and it regularly reviews encryption and security systems.

How Amy and Andrea’s device works is centred around machine learning and artificial neural networks – essentially allowing a computer work like a brain. 

It focuses on three metrics:

  • The date and time a connection is made to the toy
  • The length of time the connection lasts
  • How many times in a 24-hour period the phone connects to the toy.

It learns what behaviour is normal on the connection used by the toy, and so knows when something that isn’t normal happens. It can flag this to the parents as a potential sign of suspicious activity, which they can then review.

Amy and Andrea plan to make some final finishing touches to the device – such as ensuring it has enough ‘training’ to learn what is normal or abnormal, and adding an indicator light to the device used to analyse the connection – ahead of the exhibition next month.

 We’ll have more coverage of projects ahead of the BT Young Scientist & Technology Exhibition.

  • Share on Facebook
  • Email this article
  •  

About the author:

Nicky Ryan

Read next:

COMMENTS (7)

This is YOUR comments community. Stay civil, stay constructive, stay on topic. Please familiarise yourself with our comments policy here before taking part.
write a comment

    Leave a commentcancel