DifferentialPrivacyClientSideFixedClipping

class DifferentialPrivacyClientSideFixedClipping(strategy: Strategy, noise_multiplier: float, clipping_norm: float, num_sampled_clients: int)

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.

参数:

• 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.

实例

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, ...)	使用给定的策略汇总评估损失。
aggregate_fit(server_round, results, failures)	Add noise to the aggregated parameters.
configure_evaluate(server_round, parameters, ...)	配置下一轮评估。
configure_fit(server_round, parameters, ...)	配置下一轮训练。
evaluate(server_round, parameters)	使用策略中的评估函数评估模型参数。
initialize_parameters(client_manager)	使用给定的策略初始化全局模型参数。

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]]

使用给定的策略汇总评估损失。

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]]

Add noise to the aggregated parameters.

configure_evaluate(server_round: int, parameters: Parameters, client_manager: ClientManager) → list[tuple[ClientProxy, EvaluateIns]]

配置下一轮评估。

configure_fit(server_round: int, parameters: Parameters, client_manager: ClientManager) → list[tuple[ClientProxy, FitIns]]

配置下一轮训练。

evaluate(server_round: int, parameters: Parameters) → tuple[float, dict[str, bool | bytes | float | int | str]] | None

使用策略中的评估函数评估模型参数。

initialize_parameters(client_manager: ClientManager) → Parameters | None

使用给定的策略初始化全局模型参数。