View source on GitHub |
Creates secure aggregator with adaptive zeroing and clipping.
tff.learning.secure_aggregator(
*, zeroing: bool = True, clipping: bool = True, weighted: bool = True
) -> tff.aggregators.AggregationFactory
Zeroes out extremely large values for robustness to data corruption on
clients, clips to moderately high norm for robustness to outliers. After
weighting in mean, the weighted values are summed using cryptographic protocol
ensuring that the server cannot see individual updates until sufficient number
of updates have been added together. For details, see Bonawitz et al. (2017)
https://dl.acm.org/doi/abs/10.1145/3133956.3133982. In TFF, this is realized
using the tff.federated_secure_sum_bitwidth
operator.
Returns | |
---|---|
A tff.aggregators.AggregationFactory .
|