Why you should care about debugging machine learning models
O'Reilly on Data
DECEMBER 12, 2019
Security vulnerabilities : adversarial actors can compromise the confidentiality, integrity, or availability of an ML model or the data associated with the model, creating a host of undesirable outcomes. The study of security in ML is a growing field—and a growing problem, as we documented in a recent Future of Privacy Forum report. [8].
Let's personalize your content