AI Paper Atlas

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

On the Minimal Adversarial Perturbation for Deep Neural Networks With Provable Estimation Error

Fabio Brau, Giulio Rossolini, Alessandro Biondi, Giorgio Buttazzo

TPAMI 2022 · Adversarial robustness and security › Certified and empirical robustness · approach: Robustness-accuracy trade-off analysis · 12 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 CB strategy instead of FOB (Bisection)boundary distance estimation · MNISTaverage distance from boundary: 1.803954 -> 1.645090Improved
use CB strategy instead of FOB (Bisection)boundary distance estimation · GTSRBaverage distance from boundary: 4.885275 -> 3.665061Improved
use Bisection CB instead of Newton CB for sigma-hatboundary estimation · FMNIST (rho=sqrt2)sigma-hat: 0.02 -> 0.06Improved
use CB instead of FOB for sigma-hatboundary estimation · MNIST (rho=2)sigma-hat: 0.37 -> 0.72Improved
use CB instead of FOB for sigma-hatboundary estimation · GTSRB (rho=2)sigma-hat: 0.49 -> 0.87Improved
use DeepFool instead of CB (global vs local method)distance estimation · Fashion-MNISTaverage distance from boundary: 0.739743 -> 0.548780Mixed
use Newton instead of Bisection algorithm for CBzero finding · FMNIST (rho=sqrt2)sigma-hat: 0.06 -> 0.02Hurt
test attacks bounded by t(x)/rho* below sigma-hatCB Bisection · MNIST and GTSRBattack successImproved
test attacks bounded by t(x)/rho* below sigma-hatCB Bisection · FMNIST and CIFAR10attack successMixed

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