benchmark

UAR (Unforeseen Attack Robustness)

benchmarkactiveuar-unforeseen-attack-robustness--23d4b7c9·1 events·first seen 28d ago

Aliases: UAR (Unforeseen Attack Robustness)

Co-occurring entities

More like this (12)

adversarial robustness Latent Adversarial Robustification (LAR)Automatic Domain Randomization AuRA AUROC DARP UMAP AB-UPT Policy Vulnerability Testing Robust Classification AI Risk Management Framework Automated Reference Verification System

Recent events (1)

4Openai Blog·28d ago·source ↗

Testing Robustness Against Unforeseen Adversaries

OpenAI published a method to evaluate whether neural network classifiers can defend against adversarial attacks not encountered during training. The approach introduces a new metric called UAR (Unforeseen Attack Robustness) to quantify a model's resilience to unanticipated attacks. The work argues for measuring robustness across a broader, more diverse set of attack types rather than only those seen in training.

Evaluation and Benchmarking AI Safety Research adversarial robustness OpenAI UAR (Unforeseen Attack Robustness)