Researchers develop way to turn commands into voice-activated AI software

Nicholas Fearn
clock • 2 min read

New attacks against supposedly intelligent assistants demonstrated by US-Chinese researchers

A team of computer scientists have found a new way to trick voice-activated systems into surreptitiously executing commands embedded in popular songs. In the project, researchers in the US and C...

To continue reading this article...

Join Computing

  • Unlimited access to real-time news, analysis and opinion from the technology industry
  • Receive important and breaking news in our daily newsletter
  • Be the first to hear about our events and awards programmes
  • Join live member only interviews with IT leaders at the ‘IT Lounge’; your chance to ask your burning tech questions and have them answered
  • Access to the Computing Delta hub providing market intelligence and research
  • Receive our members-only newsletter with exclusive opinion pieces from senior IT Leaders

Join now

 

Already a Computing member?

Login

You may also like
Google Chrome can now make its own decisions on your safety

Internet

The browser's newest version can act by itself to snip out unwanted permissions

clock 13 September 2024 • 1 min read
China refuses to sign agreement on AI control of nuclear weapons

Threats and Risks

Global call to maintain human involvement in all nuclear related decisions

clock 12 September 2024 • 3 min read
Lords seek to regulate automation in public sector

Artificial Intelligence

Labour has concerns about unregulated AI

clock 11 September 2024 • 3 min read
Most read
01
02

Teen arrested over TfL cyberattack

13 September 2024 • 3 min read
03

Ransomware targets London branch of China's ICBC

13 September 2024 • 2 min read

Sign up to our newsletter

The best news, stories, features and photos from the day in one perfectly formed email.

More on Software

Ripe for change: How tech is disrupting insurance

Ripe for change: How tech is disrupting insurance

AI is 'raising the bar and raising the game'

Tom Allen
clock 13 August 2024 • 4 min read
The social engineering of the self: How AI chatbots manipulate our thinking

The social engineering of the self: How AI chatbots manipulate our thinking

We need structured public feedback to better understand the risks, says red teamer Rumman Chowdhury

John Leonard
clock 27 October 2023 • 4 min read
AI doesn't care what you think

AI doesn't care what you think

Want to understand hallucinations? Look at your family

Professor Peter Cochrane
clock 26 October 2023 • 3 min read