33 citations · 34 across the 3 of their papers we have counts for
3 papers · 1 filter
Vicious Classifiers: Assessing Inference-time Data Reconstruction Risk in Edge Computing
Mohammad Malekzadeh, Deniz Gunduz
Privacy-preserving inference in edge computing paradigms encourages the users of machine-learning services to locally run a model on their private input and only share the models o…
Quantifying and Localizing Usable Information Leakage from Neural Network Gradients
Fan Mo, Anastasia Borovykh, Mohammad Malekzadeh +3
In collaborative learning, clients keep their data private and communicate only the computed gradients of the deep neural network being trained on their local data. Several recent…
Honest-but-Curious Nets: Sensitive Attributes of Private Inputs Can Be Secretly Coded into the Classifiers' Outputs
Mohammad Malekzadeh, Anastasia Borovykh, Deniz Gündüz
It is known that deep neural networks, trained for the classification of non-sensitive target attributes, can reveal sensitive attributes of their input data through internal repre…