secretflow.security.privacy#

Classes:

`GaussianEmbeddingDP`(args, *kwargs)	Embedding differential privacy perturbation using gaussian noise
`GaussianModelDP`(noise_multiplier, num_clients)	global model differential privacy perturbation using gaussian noise
`LabelDP`(eps)	Label differential privacy perturbation
`DPStrategy`([embedding_dp, label_dp, ...])
`DPStrategyFL`([model_gdp, accountant_type])

class secretflow.security.privacy.GaussianEmbeddingDP(*args, **kwargs)[源代码]#

基类：EmbeddingDP

Embedding differential privacy perturbation using gaussian noise

Methods:

`__init__`(noise_multiplier, batch_size, ...)	param epnoise_multipliers: Epsilon for pure DP.
`call`(inputs)	Add gaussion dp on embedding.
`privacy_spent_rdp`(step[, orders])	Get accountant using RDP.
`privacy_spent_gdp`(step, sampling_type)	Get accountant using GDP.

__init__(noise_multiplier: float, batch_size: int, num_samples: int, l2_norm_clip: float = 1.0, delta: Optional[float] = None, is_secure_generator: bool = False) → None[源代码]#

参数:

epnoise_multipliers – Epsilon for pure DP.
batch_size – Batch size.
num_samples – Number of all samples.
l2_norm_clip – The clipping norm to apply to the embedding.
is_secure_generator – whether use the secure generator to generate noise.

call(inputs)[源代码]#

Add gaussion dp on embedding.

参数:: inputs – Embedding.

privacy_spent_rdp(step: int, orders: Optional[List] = None)[源代码]#

Get accountant using RDP.

参数:

step – The current step of model training or prediction.
orders – An array (or a scalar) of RDP orders.

privacy_spent_gdp(step: int, sampling_type: str)[源代码]#

Get accountant using GDP.

参数:

step – The current step of model training or prediction.
sampling_type – Sampling type, which must be “poisson” or “uniform”.

class secretflow.security.privacy.GaussianModelDP(noise_multiplier: float, num_clients: int, num_updates: Optional[int] = None, l2_norm_clip: float = 1.0, delta: Optional[float] = None, is_secure_generator: bool = False, is_clip_each_layer: bool = False)[源代码]#

基类：object

global model differential privacy perturbation using gaussian noise

Methods:

__init__(noise_multiplier, num_clients[, ...])

param epnoise_multipliers:: Epsilon for pure DP.

privacy_spent_rdp(step[, orders])

Get accountant using RDP.

__init__(noise_multiplier: float, num_clients: int, num_updates: Optional[int] = None, l2_norm_clip: float = 1.0, delta: Optional[float] = None, is_secure_generator: bool = False, is_clip_each_layer: bool = False) → None[源代码]#

参数:

epnoise_multipliers – Epsilon for pure DP.
num_clients – Number of all clients.
num_updates – Number of Clients that participate in the update.
l2_norm_clip – The clipping norm to apply to the parameters or gradients.
is_secure_generator – whether use the secure generator to generate noise.
is_clip_prelayer – The 2norm of each layer is dynamically assigned.

privacy_spent_rdp(step: int, orders: Optional[List] = None)[源代码]#

Get accountant using RDP.

参数:

step – The dp current step of model training or prediction.
orders – An array (or a scalar) of RDP orders.

class secretflow.security.privacy.LabelDP(eps: float)[源代码]#

基类：object

Label differential privacy perturbation

Methods:

__init__(eps)

param eps:: epsilon for pure DP.

privacy_spent()

__init__(eps: float) → None[源代码]#

参数:: eps – epsilon for pure DP.

privacy_spent()[源代码]#

class secretflow.security.privacy.DPStrategy(embedding_dp: Optional[EmbeddingDP] = None, label_dp: Optional[LabelDP] = None, accountant_type='rdp', sampling_type=None)[源代码]#

基类：object

Methods:

__init__([embedding_dp, label_dp, ...])

param embedding_dp:: Embedding dp layer.

get_privacy_spent(step[, orders])

Get accountant of all used dp mechanism.

__init__(embedding_dp: Optional[EmbeddingDP] = None, label_dp: Optional[LabelDP] = None, accountant_type='rdp', sampling_type=None)[源代码]#

参数:

embedding_dp – Embedding dp layer.
label_dp – Label dp layer.
accountant_type – Method of calculating accountant, which must be “rdp” or “gdp”.
sampling_type – Sampling type for GDP, which must be “poisson” or “uniform”.

get_privacy_spent(step: int, orders=None)[源代码]#

Get accountant of all used dp mechanism.

参数:

step – The current step of model training or prediction.
orders – An array (or a scalar) of RDP orders.

class secretflow.security.privacy.DPStrategyFL(model_gdp: Optional[GaussianModelDP] = None, accountant_type='rdp')[源代码]#

基类：object

Methods:

__init__([model_gdp, accountant_type])

param model_gdp:: global dp strategy on model parameters or gradients.

get_privacy_spent(step[, orders])

Get accountant of all used dp mechanism.

__init__(model_gdp: Optional[GaussianModelDP] = None, accountant_type='rdp')[源代码]#

参数:

model_gdp – global dp strategy on model parameters or gradients.
accountant_type – Method of calculating accountant, only supports “rdp”.

get_privacy_spent(step: int, orders=None)[源代码]#

Get accountant of all used dp mechanism.

参数:

step – The current step of model training or prediction.
orders – An array (or a scalar) of RDP orders.