This technique exploits the fact that the CNN is completely deterministic—see my reply above. It may be very difficult for stochastic networks.
CNNs are comparable to the first 150ms or so of human vision, before feedback , multiple saccades, and higher order mental programs kicks in. So the difficulty in generating these fooling images also depends on the complexity of the inference—a more complex AGI with human-like vision given larger amounts of time to solve the task would probably also be harder to fool, independent of the stochasticity issue.
This technique exploits the fact that the CNN is completely deterministic—see my reply above. It may be very difficult for stochastic networks.
CNNs are comparable to the first 150ms or so of human vision, before feedback , multiple saccades, and higher order mental programs kicks in. So the difficulty in generating these fooling images also depends on the complexity of the inference—a more complex AGI with human-like vision given larger amounts of time to solve the task would probably also be harder to fool, independent of the stochasticity issue.