Representation Matters in Randomized Smoothing for Audio Classification

• URL: http://arxiv.org/abs/2606.04210v1
• Date: Tue, 02 Jun 2026 20:56:05 GMT
• Title: Representation Matters in Randomized Smoothing for Audio Classification
• Abstract summary: Randomized smoothing certifies robustness in the vector space where Gaussian noise is added.<n>On two audio benchmarks, keyword spotting and environmental-sound classification, we study waveform, feature-space, and post-processed smoothing.
• Score: 30.521314184750867
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• RRISE: Robust Radius Inference via a Surrogate Estimator [30.521314184750867]
  We introduce RRISE, an RS framework that compresses certification into a single forward pass through a learned surrogate.<n>On CIFAR-100 and Tiny ImageNet, where the only prior offline-surrogate method collapses, RRISE achieves $1.23$ to $1.91times$ higher certified accuracy.
  arXiv  Detail & Related papers  (2026-06-01T20:46:06Z)
• Spectral Tempering for Embedding Compression in Dense Passage Retrieval [17.660889990235656]
  We show that the optimal scaling strength $$ is not a global constant.<n>We propose Spectral Tempering, a learning-free method that derives an adaptive $(k)$ directly from the corpus eigenspectrum.
  arXiv  Detail & Related papers  (2026-03-19T10:01:32Z)
• Phase-space entropy at acquisition reflects downstream learnability [54.4100065023873]
  We propose an acquisition-level scalar $S_mathcal B$ based on instrument-resolved phase space.<n>We show theoretically that (S_mathcal B) correctly identifies the phase-space coherence of periodic sampling.<n>$|S_mathcal B|$ consistently ranks sampling geometries and predicts downstream reconstruction/recognition difficulty emphwithout training.
  arXiv  Detail & Related papers  (2025-12-22T10:03:51Z)
• Robust Layerwise Scaling Rules by Proper Weight Decay Tuning [50.11170157029911]
  In modern scale-invariant architectures, training quickly enters an degrading-governed steady state.<n>We introduce a weight-decay scaling rule for AdamW that preserves sublayer gain across widths.<n>Our results extend $mu$P beyond the near-init regime by explicitly controlling the steady-state scales set by parameters.
  arXiv  Detail & Related papers  (2025-10-17T02:58:35Z)
• Robust Representation Consistency Model via Contrastive Denoising [83.47584074390842]
  randomized smoothing provides theoretical guarantees for certifying robustness against adversarial perturbations.<n> diffusion models have been successfully employed for randomized smoothing to purify noise-perturbed samples.<n>We reformulate the generative modeling task along the diffusion trajectories in pixel space as a discriminative task in the latent space.
  arXiv  Detail & Related papers  (2025-01-22T18:52:06Z)
• Adaptive $k$-nearest neighbor classifier based on the local estimation of the shape operator [49.87315310656657]
  We introduce a new adaptive $k$-nearest neighbours ($kK$-NN) algorithm that explores the local curvature at a sample to adaptively defining the neighborhood size. Results on many real-world datasets indicate that the new $kK$-NN algorithm yields superior balanced accuracy compared to the established $k$-NN method.
  arXiv  Detail & Related papers  (2024-09-08T13:08:45Z)
• Certified Adversarial Robustness Within Multiple Perturbation Bounds [38.3813286696956]
  Randomized smoothing (RS) is a well known certified defense against adversarial attacks. In this work, we aim to improve the certified adversarial robustness against multiple perturbation bounds simultaneously.
  arXiv  Detail & Related papers  (2023-04-20T16:42:44Z)
• Double Sampling Randomized Smoothing [19.85592163703077]
  We propose a Double Sampling Randomized Smoothing framework. It exploits the sampled probability from an additional smoothing distribution to tighten the robustness certification of the previous smoothed classifier. We show that DSRS certifies larger robust radii than existing datasets consistently under different settings.
  arXiv  Detail & Related papers  (2022-06-16T04:34:28Z)
• FedCorr: Multi-Stage Federated Learning for Label Noise Correction [80.9366438220228]
  Federated learning (FL) is a privacy-preserving distributed learning paradigm that enables clients to jointly train a global model. We propose $textttFedCorr$, a general multi-stage framework to tackle heterogeneous label noise in FL. Experiments conducted on CIFAR-10/100 with federated synthetic label noise, and on a real-world noisy dataset, Clothing1M, demonstrate that $textttFedCorr$ is robust to label noise.
  arXiv  Detail & Related papers  (2022-04-10T12:51:18Z)
• Conditioning Trick for Training Stable GANs [70.15099665710336]
  We propose a conditioning trick, called difference departure from normality, applied on the generator network in response to instability issues during GAN training. We force the generator to get closer to the departure from normality function of real samples computed in the spectral domain of Schur decomposition.
  arXiv  Detail & Related papers  (2020-10-12T16:50:22Z)
• Shape Matters: Understanding the Implicit Bias of the Noise Covariance [76.54300276636982]
  Noise in gradient descent provides a crucial implicit regularization effect for training over parameterized models. We show that parameter-dependent noise -- induced by mini-batches or label perturbation -- is far more effective than Gaussian noise. Our analysis reveals that parameter-dependent noise introduces a bias towards local minima with smaller noise variance, whereas spherical Gaussian noise does not.
  arXiv  Detail & Related papers  (2020-06-15T18:31:02Z)
• Automatic Estimation of Intelligibility Measure for Consonants in Speech [44.02658023314131]
  We train regression models based on Convolutional Neural Networks (CNN) for stop consonants. We estimate the corresponding Signal to Noise Ratio (SNR) at which the Consonant-Vowel (CV) sound becomes intelligible for Normal Hearing (NH) ears.
  arXiv  Detail & Related papers  (2020-05-12T21:45:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.