Anshuman Suri
Anshuman Suri
Home
Publications
Posts
Contact
News
Light
Dark
Automatic
3
Subject Membership Inference Attacks in Federated Learning
We propose a notion of neuron sensitivity in terms of adversarial robustness, along with an attack that works as well as PGD. The notion can be extended as a regularization term, providing adversarial robustness without adversarial training.
Anshuman Suri
,
Pallika Kanani
,
Virendra J. Marathe
,
Daniel W. Peterson
PDF
One Neuron to Fool Them All
We propose a notion of neuron sensitivity in terms of adversarial robustness, along with an attack that works as well as PGD. The notion can be extended as a regularization term, providing adversarial robustness without adversarial training.
Anshuman Suri
,
David Evans
PDF
Cite
Code
Cite
×