OpenAI Blog · Aug 22, 2019
Testing robustness against unforeseen adversaries
Reviewed by Errol Vogt, Site support technician & online learning analyst · original summary · editorial policy
Testing robustness against unforeseen adversaries. We’ve developed a method to assess whether a neural network classifier can reliably defend against adversarial attacks not seen during training. Our method yields a new metric, UAR (Unforeseen Attack Robustness), which evaluates the robustness of a single model against an unanticipated attack, and highlights the need to measure performance across a more diverse range of unforeseen attacks. This update is relevant for small-office operators tracking changes in their tools.
Operator takeaway: For operators: review whether 'Testing robustness against unforeseen adversaries' affects your current setup before relying on it in production.
ai