Mimic#

class byzfl.Mimic(epsilon=0)[source]#

Bases: object

Description#

The attacker mimics the behavior of worker with ID \(\epsilon\) by sending the same vector as that worker [1].

\[\text{Mimic}_{\epsilon}(x_1, \dots, x_n) = x_{\epsilon+1}\]

where

  • \(x_1, \dots, x_n\) are the input vectors, which conceptually correspond to correct gradients submitted by honest participants during a training iteration.

  • \(\epsilon \in \{0, \dots, n-1\}\) is the ID of the worker to mimic. In other words, \(x_{\epsilon+1}\) is the vector sent by the worker with ID \(\epsilon\).

Initialization parameters:

epsilon (int, optional) – ID of the worker whose behavior is to be mimicked. Set to 0 by default.

Calling the instance

Input parameters:

vectors (numpy.ndarray, torch.Tensor, list of numpy.ndarray or list of torch.Tensor) – A set of vectors, matrix or tensors.

Returns:

numpy.ndarray or torch.Tensor – The data type of the output is the same as the input.

Examples

>>> import byzfl
>>> attack = byzfl.Mimic(0)

Using numpy arrays:

>>> import numpy as np
>>> x = np.array([[1., 2., 3.],       # np.ndarray
>>>               [4., 5., 6.],
>>>               [7., 8., 9.]])
>>> attack(x)
array([1. 2. 3.])

Using torch tensors:

>>> import torch
>>> x = torch.tensor([[1., 2., 3.],   # torch.tensor
>>>                   [4., 5., 6.],
>>>                   [7., 8., 9.]])
>>> attack(x)
tensor([1., 2., 3.])

Using list of numpy arrays

>>> import numpy as np
>>> x = [np.array([1., 2., 3.]),      # list of np.ndarray
>>>      np.array([4., 5., 6.]),
>>>      np.array([7., 8., 9.])]
>>> attack(x)
array([1.  2. 3.])

Using list of torch tensors:

>>> import torch
>>> x = [torch.tensor([1., 2., 3.]),  # list of torch.tensor
>>>      torch.tensor([4., 5., 6.]),
>>>      torch.tensor([7., 8., 9.])]
>>> attack(x)
tensor([1., 2., 3.])

References

On this page