Microsoft unveils safety and security tools for generative AI

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 applications ai studio applications artificial intelligence attacks azure azure ai azure ai studio building cloud cloud-based cloud computing detection generative generative-ai generative ai applications hallucinations messages microsoft microsoft azure monitoring prompt prompt injection prompt injection attacks protection risk safe safety security software development studio the company toolkit tools