Search Results for author:
Found 8 papers, 2 papers with code
Inferring Sensitive Attributes from Model Explanations
We focus on the specific privacy risk of attribute inference attack wherein an adversary infers sensitive attributes of an input (e. g., race and sex) given its model explanations.
I-GWAS: Privacy-Preserving Interdependent Genome-Wide Association Studies
We introduce I-GWAS, a novel framework that securely computes and releases the results of multiple possibly interdependent GWASes.
MixNN: Protection of Federated Learning Against Inference Attacks by Mixing Neural Network Layers
Boosted by Machine Learning as a Service (MLaaS), the number of applications relying on ML capabilities is ever increasing.
Privacy Assessment of Federated Learning using Private Personalized Layers
While this scheme has been proposed as local adaptation to improve the accuracy of the model through local personalization, it has also the advantage to minimize the information about the model exchanged with the server.
GECKO: Reconciling Privacy, Accuracy and Efficiency in Embedded Deep Learning
We choose quantization as design choice for highly efficient and private models.
DYSAN: Dynamically sanitizing motion sensor data against sensitive inferences through adversarial networks
However, nothing prevents the service provider to infer private and sensitive information about a user such as health or demographic attributes. In this paper, we present DySan, a privacy-preserving framework to sanitize motion sensor data against unwanted sensitive inferences (i. e., improving privacy) while limiting the loss of accuracy on the physical activity monitoring (i. e., maintaining data utility).
