Microsoft is developing prompt shields for its generative AI tools

02/04/2024 | Fortune

Microsoft is introducing a new "prompt shield" safety feature into Azure AI Studio to prevent people from tricking its artificial intelligence chatbots into performing unintended actions. The role of prompt shields is to detect and block prompt injection attacks, which hackers use to insert malicious instructions into the data on which a model is trained. The new defences can spot suspicious inputs and block them in real-time.

Read Full Story
Microsoft Azure AI

What is this page?

You are reading a summary article on the Privacy Newsfeed, a free resource for DPOs and other professionals with privacy or data protection responsibilities helping them stay informed of industry news all in one place. The information here is a brief snippet relating to a single piece of original content or several articles about a common topic or thread. The main contributor is listed in the top left-hand corner, just beneath the article title.

The Privacy Newsfeed monitors over 300 global publications, of which more than 4,350 summary articles have been posted to the online archive dating back to the beginning of 2020. A weekly roundup is available by email every Friday.

Freevacy has been shortlisted in the Best Educator category.
The PICCASO Privacy Awards recognise the people making an outstanding contribution to this dynamic and fast-growing sector.