# Can GANs only fool the discriminator they trained against?

Suppose a GAN is trained in a typical fashion, so that it can produce images which are, to humans, imperceptibly different from images that a separate, discriminator network can correctly classify, and yet these new images will be misclassified by the discriminator network with high probability.

My question is: is the ability of the GAN to fool the discriminator specific to the particular discriminator? Suppose two discriminators were trained on slightly different data sets, or the same data set, but with different initializations for the discriminator's weights. Then would a GAN trained against one discriminator preform reasonably well on the second? Any references would be very useful.

• Please edit your question to spell out each abbreviation at its first use, or simply use the full form instead of an abbreviation. – Kodiologist Nov 11 '17 at 18:07