17.4 C
London
Friday, May 17, 2024

Microsoft releases inaugural AI transparency report

Must read

- Advertisement -


In its Accountable AI Transparency Report, which primarily covers 2023, Microsoft touts its achievements round safely deploying AI merchandise. The annual AI transparency report is among the commitments the corporate made after signing a voluntary settlement with the White Home in July final yr. Microsoft and different firms promised to ascertain accountable AI methods and decide to security.

Microsoft says within the report that it created 30 accountable AI instruments prior to now yr, grew its accountable AI group, and required groups making generative AI purposes to measure and map dangers all through the event cycle. The corporate notes that it added Content Credentials to its picture technology platforms, which places a watermark on a photograph, tagging it as made by an AI mannequin. 

The corporate says it’s given Azure AI prospects entry to instruments that detect problematic content material like hate speech, sexual content material, and self-harm, in addition to instruments to judge safety dangers. This contains new jailbreak detection strategies, which have been expanded in March this yr to incorporate oblique immediate injections the place the malicious directions are a part of knowledge ingested by the AI mannequin.

It’s additionally increasing its red-teaming efforts, together with each in-house crimson groups that intentionally attempt to bypass security options in its AI fashions in addition to red-teaming purposes to permit third-party testing earlier than releasing new fashions.

Nevertheless, its red-teaming models have their work minimize out for them. The corporate’s AI rollouts haven’t been proof against controversies.

- Advertisement -

Natasha Crampton, chief accountable AI officer at Microsoft, says in an e-mail despatched to The Verge that the corporate understands AI continues to be a piece in progress and so is accountable AI. 

“Accountable AI has no end line, so we’ll by no means contemplate our work underneath the Voluntary AI commitments achieved. However we now have made robust progress since signing them and sit up for constructing on our momentum this yr,” Crampton says. 



Source link

More articles

- Advertisement -

Latest article