AI Paper Atlas

Research map / Adversarial robustness and security / Black-box and transfer attacks

Denoised Smoothing: A Provable Defense for Pretrained Classifiers

Hadi Salman, Mingjie Sun, Greg Yang, Ashish Kapoor, J. Zico Kolter

NeurIPS 2020 · Adversarial robustness and security › Black-box and transfer attacks · approach: Robustness benchmarks and defenses · 44 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
Add a denoiser before the classifierPretrained ResNet-50 · ImageNet, ℓ2 radius 0.5certified top-1 accuracy: 4 -> 33Improved
Add a denoiser before the classifierPretrained ResNet-110 · CIFAR-10, ℓ2 radius 0.5certified accuracy: 3 -> 41Improved
Train the denoiser with Stab rather than MSE (ablation)White-box ResNet-110 · CIFAR-10certified accuracyImproved
Train the denoiser with Stab rather than Stab+MSE (ablation)White-box ResNet-110 · CIFAR-10certified accuracyImproved
Fine-tune an MSE denoiser with Stab (ablation)White-box pretrained ResNet-18/34/50 · ImageNetcertified accuracyImproved
Fine-tune an MSE denoiser with Stab using surrogate classifiers (ablation)Black-box pretrained ResNet-18/34/50 · ImageNetcertified accuracyImproved
Use 14 surrogate models rather than fewer surrogates to train the denoiser (ablation)Black-box ResNet-110 · CIFAR-10, especially larger σcertified accuracyImproved
Use MSE rather than Stab (ablation)Black-box CIFAR-10 denoiser at σ=0.50 · CIFAR-10, small ℓ2 radiicertified accuracyImproved
Use Stab+MSE rather than MSE (ablation)White-box ImageNet classifiers · ImageNetcertified accuracyImproved
Use Stab+MSE rather than MSE (ablation)Black-box pretrained classifiers · ImageNetcertified accuracyImproved
Increase Monte Carlo samples from 100 to 1000 (ablation)Azure Vision API with an MSE denoiser · ImageNet validation imagescertified accuracyImproved
Use the classification objective instead of the stability objective (ablation)Denoisers on CIFAR-10, ImageNet, and vision APIs · CIFAR-10, ImageNet, and vision APIscertified accuracyNo clear effect

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