Machine learning can turn any kind of data into mathematical equations. Once you train a machine learning model you get a set of numerical parameters. In most cases, the model no longer needs the training dataset and uses the tuned parameters to map new and unseen examples to categories or value predictions. Tech Talks brought this interesting topic to us in their article, “Machine learning: What are membership inference attacks?“
Unfortunately, a type of attack called “membership inference” makes it possible to detect the data used to train a machine learning model. In many cases, the attackers can stage membership inference attacks without having access to the machine learning model’s parameters and just by observing its output.
The result is security and privacy concerns in cases where the target model has been trained on sensitive information. These inference attacks on aggregate survey data through the use of several real-world datasets and a published study as a model for the survey is a serious problem.
Melody K. Smith
Sponsored by Access Innovations, the world leader in thesaurus, ontology, and taxonomy creation and metadata application.