nsl.configs.AdvNeighborConfig

Contains configuration for generating adversarial neighbors.

nsl.configs.AdvNeighborConfig(
    feature_mask=attr_dict['feature_mask'].default,
    adv_step_size=attr_dict['adv_step_size'].default,
    adv_grad_norm=attr_dict['adv_grad_norm'].default,
    clip_value_min=attr_dict['clip_value_min'].default,
    clip_value_max=attr_dict['clip_value_max'].default,
    pgd_iterations=attr_dict['pgd_iterations'].default,
    pgd_epsilon=attr_dict['pgd_epsilon'].default,
    random_init=attr_dict['random_init'].default
)

Attributes
`feature_mask`	mask w/ values in `[0, 1]` applied on the gradient. Its shape should be the same as (or broadcastable to) that of the input features. If the input features are in a collection (e.g. list or dictionary), this field should also be a collection of the same structure. Input features corresponding to mask values of 0.0 are not perturbed. Setting this field to `None` is equivalent to setting a mask value of 1.0 for all input features.
`adv_step_size`	step size to find the adversarial sample. Default set to 0.001.
`adv_grad_norm`	type of tensor norm to normalize the gradient. Input will be converted to `nsl.configs.NormType` when applicable (e.g., `'l2'` -> `nls.configs.NormType.L2`). Default set to L2 norm.
`clip_value_min`	minimum value to clip the features after perturbation. The shape should be the same as (or broadcastable to) input features. If the input features are in a collection (e.g. list or dictionary), this field should also be a collection with the same structure. An omitted or `None`-valued entry in the collection indicates no constraint on the corresponding feature.
`clip_value_max`	maximum value to clip the feature after perturbation. (See `clip_value_min` for the structure and shape limitations.)
`pgd_iterations`	number of attack iterations for Projected Gradient Descent (PGD) attack. Defaults to 1, which resembles the Fast Gradient Sign Method (FGSM) attack.
`pgd_epsilon`	radius of the epsilon ball to project back to. Only used in Projected Gradient Descent (PGD) attack.
`random_init`	Apply a random perturbation before FGSM/PGD steps. Default set to `False` for no random initialization being applied.