AI Paper Atlas

Research map / Adversarial robustness and security / Certified and empirical robustness

Center Smoothing: Certified Robustness for Networks with Structured Outputs

Aounon Kumar, Tom Goldstein

NeurIPS 2021 · Adversarial robustness and security › Certified and empirical robustness · approach: Certified training and ensembles · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Train the base model with Gaussian noise matching the smoothing noise (ablation)Center smoothing for total-variation certificates · MNIST and CIFAR-10 dimensionality reduction and image reconstructioncertified output radiusImproved
Increase h = ε₁/σCenter smoothing · Face detection, generative model, and total-variation experimentscertified output radiusImproved
Use a higher h such that q exceeds oneCenter smoothing certification procedure · Structured-output experimentscertification successHurt
Use center smoothing instead of the expectation-smoothed ℓ₂ baselineAutoencoder and image-reconstruction models · MNIST and CIFAR-10certified output radiusImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy