AI Paper Atlas

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

Verifying Neural Network Robustness with Dual Perturbations

Hai Duong, Lam Nguyen, Thanh Le, ThanhVu Nguyen

CVPR 2026 · Adversarial robustness and security › Certified and empirical robustness · approach: Neural network robustness verification

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 independent pixel perturbation to universal convolutional perturbation (dual)VeriDou · MNIST-FCSAT instances (%): 12% -> 75%Improved
use universal instead of restricted convolutional kernels (ablation)VeriDou · TinyImageNetSAT instances (%): 53% -> 89%Improved
use restricted convolutional perturbation instead of independent only (ablation)VeriDou · TinyImageNetSAT instances (%): 20% -> 53%Improved
add convolutional component (zij from 0.0 to 0.1) to independent perturbation (ablation)VeriDou · CIFAR100SAT instances (%): 0% -> 85%Improved
add convolutional component (zij from 0.0 to 0.1) to independent perturbation (ablation)VeriDou · TinyImageNetSAT instances (%): 20% -> 70%Improved
increase independent perturbation radius from 0.01 to 0.04 (ablation)VeriDou · MNIST-FCSAT instances (%): 21% -> 33%Improved
increase independent perturbation radius from 0.01 to 0.04 (ablation)VeriDou · Oval21SAT instances (%): 15% -> 20%Improved
add independent noise to universal kernels on continuous angle ranges (ablation)VeriDou alpha-beta · Continuous kernel angle rangesSAT count: 142 -> 171Improved
increase kernel entry coverage from 20% to 100% for arbitrary kernels (ablation)VeriDou NeuralSAT · Arbitrary kernels (Domain 3)timeout instances: 75 -> 165Hurt
increase number of evaluated samples from 300 to 600 (ablation)VeriDou NeuralSAT · Motion 0 degreesSAT fraction (dual C=1.0): 0.68 -> 0.76No clear effect
switch between verifier backends or perturbation types on runtimeVeriDou · runtime comparisonruntimeNo 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