Network Traffic Obfuscation against Traffic Classification

Algorithm 2

Improved MIM 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; attenuation factor μ.
	output: adversarial sample.
(1)	;
(2)	;
(3)	for to do
(4)	get gradient of func f with respect to ;
(5)	//update momentum
(6)
(7)	//update adversarial sample
(8)
(9)	if then
(10)	//modify
(11)
(12)	set all elements greater than 0 in the vector to
(13)	0;
(14)	;
(15)	end if
	end for.
	return.