Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Training a Tokenizer for Free with Private Federated Learning



Eugene Bagdasaryan , Congzheng Song , Rogier van Dalen , Matt Seigel , Áine Cahill


   Access Paper or Ask Questions

Spinning Language Models for Propaganda-As-A-Service



Eugene Bagdasaryan , Vitaly Shmatikov

* arXiv admin note: text overlap with arXiv:2107.10443 

   Access Paper or Ask Questions

Towards Sparse Federated Analytics: Location Heatmaps under Distributed Differential Privacy with Secure Aggregation



Eugene Bagdasaryan , Peter Kairouz , Stefan Mellem , Adrià Gascón , Kallista Bonawitz , Deborah Estrin , Marco Gruteser


   Access Paper or Ask Questions

Spinning Sequence-to-Sequence Models with Meta-Backdoors



Eugene Bagdasaryan , Vitaly Shmatikov


   Access Paper or Ask Questions

Blind Backdoors in Deep Learning Models



Eugene Bagdasaryan , Vitaly Shmatikov


   Access Paper or Ask Questions

Decentralized Policy-Based Private Analytics



Kleomenis Katevas , Eugene Bagdasaryan , Jason Waterman , Mohamad Mounir Safadieh , Hamed Haddadi , Deborah Estrin


   Access Paper or Ask Questions

Salvaging Federated Learning by Local Adaptation



Tao Yu , Eugene Bagdasaryan , Vitaly Shmatikov


   Access Paper or Ask Questions

Differential Privacy Has Disparate Impact on Model Accuracy



Eugene Bagdasaryan , Vitaly Shmatikov


   Access Paper or Ask Questions

How To Backdoor Federated Learning



Eugene Bagdasaryan , Andreas Veit , Yiqing Hua , Deborah Estrin , Vitaly Shmatikov


   Access Paper or Ask Questions