Representation Matters in Randomized Smoothing for Audio Classification

arXiv:2606.04210v1 Announce Type: cross Abstract: Randomized smoothing (RS) certifies robustness in the vector space where Gaussian noise is added. In audio classification, this space is often not uniquely defined as standard pipelines normalize, range-control, and transform waveforms into log-mel or other spectral features. We show that direct RS is therefore under-specified unless the certified object and preprocessing policy are explicit. On two audio benchmarks, keyword spotting and environmental-sound classification, we study waveform, feature-space, and post-processed smoothing. Our diagnostics show why representation-aware reporting is necessary: at the same smoothing level sigma=0.0025, the two datasets share the same median raw radius .007996, but different waveform energies yield different SNR-equivalent scales (83.98 vs. 90.97 dB); log-mel smoothing gives higher positive-radius certified accuracy on environmental sounds (68.42% vs. 65.53%), certifying more examples with nonzero radius but over features rather than waveforms; and clipping or peak normalization changes the effective perturbation norm by roughly 230--351imes. We therefore recommend that audio RS studies choose and report the task-specific certified object and perturbation model, including the perturbation location, gain policy, raw radius, and any post-noise geometry changes.

Source: arXiv cs.LG | 2026-06-04