AI Paper Atlas

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

On the Certified Robustness for Ensemble Models and Beyond

Zhuolin Yang, Linyi Li, Xiaojun Xu, Bhavya Kailkhura, Tao Xie, Bo Li

ICLR 2022 · Adversarial robustness and security › Certified and empirical robustness · approach: Certified training and ensembles · 7 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 DRT to WE with SmoothAdv base modelsWE · MNIST, L2 radius 2.50certified accuracy: 25.0 -> 34.8Improved
Add DRT to WE with SmoothAdv base modelsWE · CIFAR-10, L2 radius 1.50certified accuracy: 23.4 -> 30.3Improved
Add DRT to WE with SmoothAdv base modelsWE · CIFAR-10, L2 radius 2.00certified accuracy: 17.5 -> 20.3Improved
Add DRT to MME with SmoothAdv base modelsMME · ImageNet, L2 radius 3.00certified accuracy: 21.6 -> 23.4Improved
Add the Gradient Diversity loss (ablation)DRT ensemble · MNIST and CIFAR-10certified accuracyImproved
Add the Confidence Margin loss (ablation)DRT ensemble · MNIST and CIFAR-10certified accuracyImproved
Add the Gradient Diversity loss (ablation)DRT ensemble · MNIST and CIFAR-10, larger radiicertified accuracyImproved
Combine Gradient Diversity and Confidence Margin losses (ablation)DRT ensemble · MNIST and CIFAR-10, all radiicertified accuracyImproved

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