Request For Research Presentations For the PrivacyCon Conference #00030

Submission Number:
00030
Commenter:
Matthew Fredrikson
State:
Pennsylvania
Initiative Name:
Request For Research Presentations For the PrivacyCon Conference
This work examines privacy issues related to a widely-used class of machine learning models, and shows that giving untrusted parties access to such models--either through APIs, applications, or published results--can reveal sensitive information about the training data, or lead to re-identification of individuals in the data. This work will appear at the ACM Conference on Computer and Communications Security (CCS) in October 2015.