WMAttack automates finite-budget attack search for world-model agents via SCAS and RGAR, reporting higher normalized reward drops than baselines on Atari and DMC tasks.
Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
AD-CERT uses logit-level adversarial distillation from a robust teacher combined with IBP to achieve state-of-the-art certified performance on robustness benchmarks, improving over feature-space distillation by up to 5.40 percentage points.
citing papers explorer
-
WMAttack: Automated Attack Search for Adversarial Evaluation of World-Model Agents
WMAttack automates finite-budget attack search for world-model agents via SCAS and RGAR, reporting higher normalized reward drops than baselines on Atari and DMC tasks.
-
Improving Certified Robustness via Adversarial Distillation
AD-CERT uses logit-level adversarial distillation from a robust teacher combined with IBP to achieve state-of-the-art certified performance on robustness benchmarks, improving over feature-space distillation by up to 5.40 percentage points.