Top
image credit: Unsplash

Microsoft unveils safety and security tools for generative AI

March 29, 2024

Via: InfoWorld
Category:
Microsoft is adding safety and security tools to Azure AI Studio, the company’s cloud-based toolkit for building generative AI applications. The new tools include protection against prompt injection attacks, detection of hallucinations in model output, system messages to steer models toward safe output, model safety evaluations, and risk and safety monitoring.

Microsoft announced the new features on March 28. Safety evaluations are now available in preview in Azure AI Studio. The other features are coming soon, Microsoft said. Azure AI Studio, also in preview, can be accessed from ai.azure.com.

Read More on InfoWorld

RELATED PUBLICATIONS

Microsoft wants to show you ads in Windows 11’s Start menu. Here’s how to prevent them
Feds say Microsoft security ‘requires an overhaul’ — but will it listen?
Microsoft’s lock screen cards for Windows 11 are about to arrive – and a much-needed addition will follow

Latest Publications

Android versions: A living history from 1.0 to 15
Salesforce launches Einstein Copilot for general availability
There is no escape from Google Meet: Meetings now seamlessly follow you anywhere
Software Curated Copyright © 2024. All rights reserved
Go to ITCurated!