43 citations · 91 across the 13 of their papers we have counts for
6 papers · 1 filter
Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples
Alexandra Souly, Javier Rando, Ed Chapman +10
Poisoning attacks can compromise the safety of large language models (LLMs) by injecting malicious documents into their training data. Existing work has studied pretraining poisoni…
Private Collaborative Edge Inference via Over-the-Air Computation
Selim F. Yilmaz, Burak Hasircioglu, Li Qiao +1
We consider collaborative inference at the wireless edge, where each client's model is trained independently on its local dataset. Clients are queried in parallel to make an accura…
Communication Efficient Private Federated Learning Using Dithering
Burak Hasircioglu, Deniz Gunduz
The task of preserving privacy while ensuring efficient communication is a fundamental challenge in federated learning. In this work, we tackle this challenge in the trusted aggreg…
Privacy Amplification via Random Participation in Federated Learning
Burak Hasircioglu, Deniz Gunduz
Running a randomized algorithm on a subsampled dataset instead of the entire dataset amplifies differential privacy guarantees. In this work, in a federated setting, we consider ra…
Over-the-Air Ensemble Inference with Model Privacy
Selim F. Yilmaz, Burak Hasircioglu, Deniz Gunduz
We consider distributed inference at the wireless edge, where multiple clients with an ensemble of models, each trained independently on a local dataset, are queried in parallel to…
Dopamine: Differentially Private Federated Learning on Medical Data
Mohammad Malekzadeh, Burak Hasircioglu, Nitish Mital +3
While rich medical datasets are hosted in hospitals distributed across the world, concerns on patients' privacy is a barrier against using such data to train deep neural networks (…