Challenging the Adversarial Robustness of DNNs Based on Error-Correcting Output Codes

Algorithm 1

Solving optimization in (6).

	Input:
	The start point and number of binary search , ;
	The step size and max iteration of gradient descent, , ;
	To be attacked image, ;
	Output:
	Adversarial perturbation
(1)
(2)
(3)	fordo
(4)
(5)
(6)	fordo
(7)	if is adversarial and then
(8)
(9)	end if
(10)	, where is the gradient of equation (6) with current w.r.t. the perturbation
(11)	end for
(12)	ifthen
(13)
(14)	else
(15)
(16)	end if
(17)	ifthen
(18)
(19)	else
(20)
(21)	end if
(22)	end for