14 citations · 14 across the 1 of their papers we have counts for
3 papers
cs.LG2019
Privacy Leakage Avoidance with Switching Ensembles
Rauf Izmailov, Peter Lin, Chris Mesterharm +1
We consider membership inference attacks, one of the main privacy issues in machine learning. These recently developed attacks have been proven successful in determining, with conf…
cs.LG2019
On Second-Order Group Influence Functions for Black-Box Predictions
Samyadeep Basu, Xuchen You, Soheil Feizi
With the rapid adoption of machine learning systems in sensitive applications, there is an increasing need to make black-box models explainable. Often we want to identify an influe…
cs.LG2019★ 14 cited
Membership Model Inversion Attacks for Deep Networks
Samyadeep Basu, Rauf Izmailov, Chris Mesterharm
With the increasing adoption of AI, inherent security and privacy vulnerabilities formachine learning systems are being discovered. One such vulnerability makes itpossible for an a…