Robustness verification

groot.verification.kantchelian_attack

KantchelianAttackWrapper (AttackWrapper)

adversarial_examples(self, X, y, order, options={})

Create adversarial examples for each input sample. This method has to be overriden!

Parameters:

Name	Type	Description	Default
X	array-like of shape (n_samples, n_features)	Samples to attack.	required
y	array-like of shape (n_samples,)	True labels for the samples.	required
order	{0, 1, 2, inf}	L-norm order to use. See numpy documentation of more explanation.	required
options	dict	Extra attack-specific options.	{}

Returns:

Type	Description
ndarray of shape (n_samples, n_features)	Adversarial examples.

attack_feasibility(self, X, y, order, epsilon, options={})

Determine whether an adversarial example is feasible for each sample given the maximum perturbation radius epsilon.

Parameters:

Name	Type	Description	Default
X	array-like of shape (n_samples, n_features)	Samples to attack.	required
y	array-like of shape (n_samples,)	True labels for the samples.	required
order	{0, 1, 2, inf}	L-norm order to use. See numpy documentation of more explanation.	required
epsilon	float	Maximum distance by which samples can move.	required
options	dict	Extra attack-specific options.	{}

Returns:

Type	Description
ndarray of shape (n_samples,) of booleans	Vector of True/False. Whether an adversarial example is feasible.