Network Traffic Obfuscation against Traffic Classification

Algorithm 1

Improved BIM using method 1.

	Input: classifier f; loss function J; original sample x; authentic label y; disturbance size α; fixed number of iterations n; number of iterations T.
	output: adversarial sample.
(1)	;
(2)	;
(3)	for to do
(4)	get gradient of func f with respect to ;
(5)	//update the adversarial sample
(6)
(7)	if then
(8)	//modify
(9)
(10)	set all elements greater than 0 in the vector to
(11)	0;
(12)	;
(13)	end if
	end for.
	return ;