AI
Reducing Privacy leaks in AI: Two approaches to contextual integrity

Reducing Privacy leaks in AI: Two approaches to contextual integrity

Microsoft Research · Tue, 25 Nov 2025 17:00:00 +0000

As AI agents become more autonomous in handling tasks for users, it's crucial they adhere to contextual norms around what information to share—and what to keep private. The theory of contextual integr...