Defense

Releasing graph neural networks with differential privacy guarantees
With the increasing popularity of graph neural networks (GNNs) in several sensitive applications like healthcare and medicine, concerns …
Iyiola E. Olatunji, Thorben Funke, Megha Khosla
PDF Cite Code
Achieving differential privacy for k-nearest neighbors based outlier detection by data partitioning
When applying outlier detection in settings where data is sensitive, mechanisms which guarantee the privacy of the underlying data are …
Jens Rauch, Iyiola E. Olatunji, Megha Khosla
PDF Cite