Closed Lan555 closed 3 years ago
yes, In case of the impersnonation attack, you sholud increase cosine distance between x_adv and the target image.
Since my code is the implementation of dodging attack, we should decrease cosine distance.
thanks
So I increase cosine distance, and put x_adv = y as the initial point of x_adv rather than x_adv = radom. But problem is x_adv will become x, why?
So your objective is make a x_adv that looks like x but classified as y. isn't it ? Since there is distance loss between x and x_adv, the image will get closer to x. Consider distance loss and not just cosine distance
So you mean in order to generate the impersnonation attack, It's not only just changing inital x_adv and "cosdistance < best_thresh" to "cosdistance > best_thresh", but also have some other operation?
I think you're right. According the original paper, changing the initial x_adv and increasing cos distance will be enough. If it doesn't work well, I think the problem will come from other parts like covariance or p_c . Thanks.
why if cosdistance < best_thresh, C=0. If I choose the Impersonation attack, should I change it to cosdistance > best_thresh?