Testing robustness against unforeseen adversaries

OpenAI Blog · 6 years ago

Researchers created a method to measure how well neural networks resist adversarial attacks they haven't encountered before, introducing a metric called UAR (Unforeseen Attack Robustness). The metric evaluates a single model's performance against unanticipated attacks rather than only those seen during training. This work emphasizes the importance of testing AI systems across a broader spectrum of novel attack types to better understand their real-world vulnerability.