AI Paper Atlas

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

GradDiv: Adversarial Robustness of Randomized Neural Networks via Gradient Diversity Regularization

Sungyoon Lee, Hoki Kim, Jaewook Lee

TPAMI 2022 · Adversarial robustness and security › Certified and empirical robustness · approach: Adversarial training refinements · 65 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 GradDiv regularizationAdv-BNN · CIFAR10combined robust accuracy (%): 42.95 -> 45.77Improved
add GradDiv regularizationAdv-BNN · CIFAR10clean accuracy (%): 75.78 -> 77.51Improved
add GradDiv regularizationAdv-BNN · CIFAR10EOT-PGD accuracy (%): 43.39 -> 45.88Improved
add GradDiv regularizationAdv-BNN · CIFAR10EOT-APGDCE accuracy (%): 59.74 -> 68.91Improved
add GradDiv regularizationAdv-BNN · CIFAR10PGD accuracy (%): 66.32 -> 75.72Improved
add GradDiv regularizationAdv-BNN · CIFAR10B&B accuracy (%): 75.09 -> 75.38No clear effect
add GradDiv regularizationAdv-BNN · CIFAR10FAB accuracy (%): 74.94 -> 77.04No clear effect
add GradDiv regularizationAdv-BNN · CIFAR10FAB accuracy vs RSE (%): 83.37 -> 77.04Hurt
add GradDiv regularizationAdv-BNN · MNISTsample MRL of gradients: 0.64 -> 0.15Improved
add GradDiv regularizationAdv-BNN · MNISTEOT-PGD accuracy gain at eps 0.36, 0.38, 0.4: +37.52%p, +37.72%p, +15.55%pImproved
add GradDiv regularizationAdv-BNN · STL10EOT-PGD accuracyImproved
add GradDiv-DPP regularizationAdv-BNN · MNISTtransfer attack accuracy among sample models (%): 24 -> 75Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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