Certified Robustness under Heterogeneous Perturbations via Hybrid Randomized Smoothing

ArXi:2605.12876v1 Announce Type: new Randomized smoothing provides strong, model-agnostic robustness certificates, but existing guarantees are limited to single modalities, treating continuous and discrete inputs in isolation. This limitation becomes critical in multimodal models, where decisions depend on cross-modal semantics and adversaries can jointly perturb heterogeneous inputs, rendering unimodal certificates insufficient. We