Research

Testing robustness against unforeseen adversaries

Source: OpenAI News 22 Aug 2019

Listen to Brief

AI audio in English, based on the NadiAI brief and original source.

Brief

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.

Why It Matters

Mengukur ketahanan terhadap serangan tidak dijangka membantu pembangun memahami batasan model dan meningkatkan keselamatan aplikasi pembelajaran mesin.

Keep Reading on NadiAI

Selected Related Articles