SOURCE-LINKED INTELLIGENCE

Discovering Natural Transformation Vulnerabilities in Black-Box Vision Models

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Natural adversarial examples (NAEs) reveal that vision models can fail under realistic semantic changes beyond norm-bounded perturbations. However, generating NAEs in a black-box setting remains challenging because existing generative attacks often rely on surrogate models, learned attack priors, or costly query-based optimization, whereas the natural transformations that expose model vulnerabilities are unknown a priori. We propose \textbf{Adversarial Scenario Attack (ASA)}, a query-based black-box framework that searches over natural-language editing scenarios using a multimodal language mod

Read original source ↗ Open in workspace

recordType

paper

region

Global