In this paper, we investigate how to extend the MFLD framework to convex optimization problems over signed measures.

Thiscanbe formulated into anon-linear equality constrained optimization problem. Unlike GANs, solving such problem iscomputationally challenging, wethen proposed a simple yet effective procedure to decouple the alternating updates for the two networks for stability. By teaching the perturbation generator to hijacking the training trajectory of the victim classifier, the generator can thus learn to move against thevictim classifier stepbystep.