{"ID":3053243,"CreatedAt":"2026-06-04T04:41:36.695875263Z","UpdatedAt":"2026-06-05T20:41:05.129451022Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.04210","arxiv_id":"2606.04210","title":"Representation Matters in Randomized Smoothing for Audio Classification","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 $σ=0.0025$, 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 $230$--$351\\times$. 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.","short_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-s...","url_abs":"https://arxiv.org/abs/2606.04210","url_pdf":"https://arxiv.org/pdf/2606.04210v1","authors":"[\"Jong-Ik Park\",\"Shreyas Chaudhari\",\"José M. F. Moura\",\"Carlee Joe-Wong\"]","published":"2026-06-02T20:56:05Z","proceeding":"eess.AS","tasks":"[\"eess.AS\",\"cs.LG\",\"cs.SD\"]","methods":"[]","has_code":false}