Previous columns in this series introduced the problem of data protection in machine learning (ML), emphasizing the real challenge that operational query data pose. That is, when you use an ML system, ...

Researchers devised a way to maintain an AI model's accuracy while ensuring attackers can't extract sensitive information used to train it. The approach is computationally efficient, reducing a ...

Subject: Mandatory Sensitive But Unclassified Information (SBU) Training. NASA Security Program Procedural Requirements, NPR 1600.1 Chapter 5, 5.24, requires the protection of Sensitive But ...