Pith. sign in

Advances and open problems in federated learning,

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.LG 1

years

2026 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

MaxModShift: Model Privacy via Designed Shifts

cs.LG · 2026-08-10 · conditional · novelty 5.0

A shift design that maximizes the eavesdropper's final model error under a power constraint is derived for federated learning, with simulations showing better privacy than ModShift at 24% of its power.

citing papers explorer

Showing 1 of 1 citing paper.

  • MaxModShift: Model Privacy via Designed Shifts cs.LG · 2026-08-10 · conditional · none · ref 1

    A shift design that maximizes the eavesdropper's final model error under a power constraint is derived for federated learning, with simulations showing better privacy than ModShift at 24% of its power.