On the security relevance of weights in deep learning.

By Kathrin Grosse, Thomas Alexander Trost, Marius Mosbach, Michael Backes, Dietrich Klakow. 2020

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Tao Yu
2. Eugene Bagdasarian
3. Vitaly Shmatikov
4. Vitaly Feldman
5. Congzheng Song
6. Florian Tramèr
7. Lingjuan Lyu
8. Reza Shokri

Citations in the corpus

• Salvaging Federated Learning by Local Adaptation (2020, methodology): “As a consequence, the federated model is so bad for these participants than when it is used to initialize local adaptation, the final adapted model still has poor accuracy (Grosse et al., 2019; Hanin & Rolnick, 2018).”