AI Paper Atlas

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

Adversarial Robustness Via Fisher-Rao Regularization

Marine Picot, Francisco Javier Messina, Malik Boudiaf, Fabrice Labeau, Ismail Ben Ayed, Pablo Piantanida

TPAMI 2022 · Adversarial robustness and security › Certified and empirical robustness · approach: Theory of adversarial risk · 37 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
use Fisher-Rao regularizer instead of KL (TRADES) (ablation)FIRE · CIFAR-10 (eps 8/255, no extra data)AutoAttack accuracy: 50.47 -> 51.45Improved
use Fisher-Rao regularizer instead of KL (TRADES) (ablation)FIRE · CIFAR-100 (eps 8/255)AutoAttack accuracy: 25.89 -> 26.42Improved
use Fisher-Rao regularizer instead of KL (TRADES) (ablation)FIRE · MNIST (eps 0.3)AutoAttack accuracy: 94.27 -> 94.44Improved
use Fisher-Rao regularizer instead of Hellinger (ablation)FIRE · CIFAR-10 (eps 8/255, no extra data)AutoAttack accuracy: 50.52 -> 51.45Improved
use Fisher-Rao regularizer instead of Hellinger (ablation)FIRE · CIFAR-100 (eps 8/255)AutoAttack accuracy: 25.58 -> 26.42Improved
use Fisher-Rao regularizer instead of Hellinger (ablation)FIRE · MNIST (eps 0.3)AutoAttack accuracy: 94.03 -> 94.44Improved
use FIRE instead of TRADES to reduce training timeFIRE · CIFAR-10 (eps 8/255, no extra data)training runtime: 17h49 -> 11h00Improved
use FIRE instead of Overfitting method for training timeFIRE · CIFAR-10 (eps 8/255, no extra data)training runtime: 42h01 -> 11h00Improved
combine FIRE with Self AdaptiveSelf Adaptive · CIFAR-10 (eps 8/255, no extra data)AutoAttack accuracy: 53.11 -> 53.26No clear effect
use FIRE with 80M-TI extra data instead of RST-advFIRE · CIFAR-10 (eps 8/255, with 80M-TI extra data)AutoAttack accuracy: 59.69 -> 59.97Improved
use FIRE instead of Overfitting methodWRN-34-10 · CIFAR-100 (eps 8/255)natural accuracy: 59.22 -> 61.03Improved
use FIRE instead of Overfitting methodWRN-34-10 · CIFAR-10 (eps 8/255, no extra data)AutoAttack accuracy: 51.72 -> 51.45No 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