New model to identify 'blind spots' in AI systems developed by MIT researchers

clock
New model by MIT researchers could be used to improve the safety factor in self-driving vehicles
Image:

New model by MIT researchers could be used to improve the safety factor in self-driving vehicles

Model could be used to improve the safety of AI used by self-driving vehicles and autonomous robots

Artificial intelligence (AI) systems can sometimes miss important details and commit major errors. But researchers from the Massachusetts Institute of Technology (MIT) and Microsoft claim to have d...

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

More on Threats and Risks

CISA issues warning on active exploitation of the PwnKit vulnerability

CISA issues warning on active exploitation of PwnKit Linux vulnerability

All US federal agencies that fall under the Federal Civilian Executive Branch are required to secure their systems against the bug by July 18

clock 30 June 2022 • 2 min read
The exploit means anyone can potentially locate secret military bases by uploading fake running data - underscoring the importance of IoT protection and security

Strava fitness app used to spy on Israeli military officials

The flaw has also exposed the locations of a number of sensitive sites in the country.

clock 21 June 2022 • 3 min read
Hertzbleed vulnerabiity in AMD and Intel CPUs could leak cryptographic keys

Hertzbleed vulnerabiity in AMD and Intel CPUs could leak cryptographic keys

Intel says an attack probably wouldn't work outside a lab environment

John Leonard
clock 16 June 2022 • 2 min read