Efficient Privacy-Aware Federated Learning by Elimination of Downstream Redundancy
Research output: Contribution to journal › Research article › Contributed › peer-review
Contributors
Details
| Original language | English |
|---|---|
| Pages (from-to) | 73-81 |
| Number of pages | 9 |
| Journal | IEEE design & test of computers : D & T |
| Volume | 39 |
| Issue number | 3 |
| Publication status | Published - 2 Mar 2021 |
| Peer-reviewed | Yes |
External IDs
| unpaywall | 10.1109/mdat.2021.3063373 |
|---|---|
| WOS | 000803107400013 |
| dblp | journals/dt/LohanaRRK22 |
Keywords
Research priority areas of TU Dresden
DFG Classification of Subject Areas according to Review Boards
ASJC Scopus subject areas
Keywords
- federated learning, homomorphic encryption, neural networks, Data privacy, Privacy, Neural networks, Training data, Collaborative work, Data models, Encryption, Cryptography, Homomorphic encryption