Transferable Adversarial Attacks against Automatic Modulation Classifier in Wireless Communications

Algorithm 2

AL-MIM.

Input: A classifier truncated model ; original signal sample to be attacked ; target signal sample ; clean signal sample ; Loss Function .

Parameter:perturbation size =0.001, number of iterations T.

Output:the adversarial example that satisfy

;

put into ,obtain feature ;

put into ,obtain feature ;

put into ,obtain feature ;

put into ,obtain feature ;

  t =0 to T-1

calculate

put into ,obtain feature

Obtain the gradient ,

where ;

update the with gradient method

 end for

return