Microsoft is launching an automation tool to help security professionals and machine learning engineers identify risks in generative AI (GenAI) systems.
According to Microsoft, the new red teaming tool, named PyRIT, increases efficiency by flagging risks that require further investigation and automating tasks.
Red teaming is a term given to security testing where a group pretends to be an enemy.
Microsoft said red teaming GenAI is different from traditional AI, due to GenAI having wider architecture variations. GenAI also requires the need to identify security risks and responsible AI risks.
“PyRIT was created in response to our belief that the sharing of AI red teaming resources across the industry raises all boats,” Microsoft wrote in a blog post on Thursday (22 February).
“We encourage our peers across the industry to spend time with the toolkit and see how it can be adopted for red teaming your own GenAI application,” the company added.
PyRIT allows users to control the execution of an AI red team operation and automatically changes strategies based on the responses given by the GenAI system.
Research and analysis company GlobalData forecasts that the overall AI market will be worth $909bn by 2030, having grown at a compound annual rate of 35% between 2022 and 2030.
In the GenAI space, revenues are expected to grow from $1.8bn in 2022 to $33bn in 2027.