DifferentialPrivacyClientSideFixedClipping#

class DifferentialPrivacyClientSideFixedClipping(strategy: Strategy, noise_multiplier: float, clipping_norm: float, num_sampled_clients: int)[source]#

Bases : Strategy

Strategy wrapper for central DP with client-side fixed clipping.

Use fixedclipping_mod modifier at the client side.

In comparison to DifferentialPrivacyServerSideFixedClipping, which performs clipping on the server-side, DifferentialPrivacyClientSideFixedClipping expects clipping to happen on the client-side, usually by using the built-in fixedclipping_mod.

Paramètres:

strategy (Strategy) – The strategy to which DP functionalities will be added by this wrapper.
noise_multiplier (float) – The noise multiplier for the Gaussian mechanism for model updates. A value of 1.0 or higher is recommended for strong privacy.
clipping_norm (float) – The value of the clipping norm.
num_sampled_clients (int) – The number of clients that are sampled on each round.

Exemples

Create a strategy:

>>> strategy = fl.server.strategy.FedAvg(...)

Wrap the strategy with the DifferentialPrivacyClientSideFixedClipping wrapper:

>>> dp_strategy = DifferentialPrivacyClientSideFixedClipping(
>>>     strategy, cfg.noise_multiplier, cfg.clipping_norm, cfg.num_sampled_clients
>>> )

On the client, add the fixedclipping_mod to the client-side mods:

>>> app = fl.client.ClientApp(
>>>     client_fn=client_fn, mods=[fixedclipping_mod]
>>> )

Methods

`aggregate_evaluate`(server_round, results, ...)	Aggregate evaluation losses using the given strategy.
`aggregate_fit`(server_round, results, failures)	Add noise to the aggregated parameters.
`configure_evaluate`(server_round, parameters, ...)	Configure the next round of evaluation.
`configure_fit`(server_round, parameters, ...)	Configure the next round of training.
`evaluate`(server_round, parameters)	Evaluate model parameters using an evaluation function from the strategy.
`initialize_parameters`(client_manager)	Initialize global model parameters using given strategy.

aggregate_evaluate(server_round: int, results: List[Tuple[ClientProxy, EvaluateRes]], failures: List[Tuple[ClientProxy, EvaluateRes] | BaseException]) → Tuple[float | None, Dict[str, bool | bytes | float | int | str]][source]#: Aggregate evaluation losses using the given strategy.

aggregate_fit(server_round: int, results: List[Tuple[ClientProxy, FitRes]], failures: List[Tuple[ClientProxy, FitRes] | BaseException]) → Tuple[Parameters | None, Dict[str, bool | bytes | float | int | str]][source]#: Add noise to the aggregated parameters.

configure_evaluate(server_round: int, parameters: Parameters, client_manager: ClientManager) → List[Tuple[ClientProxy, EvaluateIns]][source]#: Configure the next round of evaluation.

configure_fit(server_round: int, parameters: Parameters, client_manager: ClientManager) → List[Tuple[ClientProxy, FitIns]][source]#: Configure the next round of training.

evaluate(server_round: int, parameters: Parameters) → Tuple[float, Dict[str, bool | bytes | float | int | str]] | None[source]#: Evaluate model parameters using an evaluation function from the strategy.

initialize_parameters(client_manager: ClientManager) → Parameters | None[source]#: Initialize global model parameters using given strategy.