“We’ve identified that our machine learning model, which safeguards Exchange Online against risky email messages, is incorrectly identifying legitimate email messages as spam due to their similarity to email messages used in spam attacks, which is resulting in impact,” Microsoft explained in its initial acknowledgment of the problem. Just last week, Microsoft mitigated another machine learning issue that incorrectly flagged Adobe emails as spam, and in March addressed a similar problem causing incorrect quarantining of legitimate messages. In their final update on May 1, Microsoft confirmed: “After a period of monitoring, we’ve confirmed through our service health telemetry that the completion of reverting to the previous ML model has successfully remediated impact”. Microsoft suggested creating custom allow rules to ensure Gmail messages weren’t incorrectly flagged.
This Cyber News was published on cybersecuritynews.com. Publication date: Fri, 02 May 2025 12:15:10 +0000