Detecting Offensive Language with Office 365 Supervision Policies

Office 365 supervision policies can now make use of artificial intelligence and machine learning to detect offensive language in email and Teams communications. The data model covers a wide range of problematic language, but only in English. You can go ahead and cheerfully continue to swear in French, German, and other languages with no danger of being detected by policy.

Advertisements

New Office 365 Admin Center Offers to Create DLP Policy

In a sign of how automation based on signals gathered by Office 365 will emerge to help administrators do a better job, the preview of the new Admin Center offered to create a DLP policy to protect some sensitive information that I had clearly overlooked. Well-intended as the portal was, its efforts to create the new policy failed. That’s not really important – it’s the glimpse into the future which is.

Protecting Email Holding Sensitive Data

Office 365 offers different ways to apply encryption to important messages. When those messages hold sensitive data known to Office 365, like credit cards or passport numbers, we can define a transport rule or DLP policy to protect outbound email automatically. And while you can define rules and policies through the GUI, PowerShell is available too.