ReasonBreak demonstrates up to 89% attack success on reasoning and 72% on trajectories in NVIDIA Alpamayo VLA models via black-box textual perturbations, introducing a reasoning-aware evaluation framework and benchmark for autonomous driving.
Evaluating decision optimality of autonomous driving via metamorphic testing
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
PtoP uses SVGD to create diverse, failure-inducing seeds for ADS testing, boosting violation rates by up to 27.68% and diversity by 9.6% over baselines.
CoCoMagic applies constrained cooperative co-evolution to metamorphic and differential testing to find up to 287% more distinct behavioral divergences in an end-to-end ADS than baseline search methods.
citing papers explorer
-
ReasonBreak: Probing Vulnerabilities in Reasoning-Enabled Vision-Language-Action Models for Autonomous Driving
ReasonBreak demonstrates up to 89% attack success on reasoning and 72% on trajectories in NVIDIA Alpamayo VLA models via black-box textual perturbations, introducing a reasoning-aware evaluation framework and benchmark for autonomous driving.
-
From Particles to Perils: SVGD-Based Hazardous Scenario Generation for Autonomous Driving Systems Testing
PtoP uses SVGD to create diverse, failure-inducing seeds for ADS testing, boosting violation rates by up to 27.68% and diversity by 9.6% over baselines.
-
Constrained Co-evolutionary Metamorphic Differential Testing for Autonomous Systems with an Interpretability Approach
CoCoMagic applies constrained cooperative co-evolution to metamorphic and differential testing to find up to 287% more distinct behavioral divergences in an end-to-end ADS than baseline search methods.