AI Paper Atlas

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

Sensitivity Analysis of Deep Neural Networks

Hai Shu, Hongtu Zhu

AAAI 2019 · Adversarial robustness and security › Certified and empirical robustness · approach: Robustness-accuracy trade-off analysis · 82 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 the proposed FI measure instead of the Jacobian norm for simulated-outlier detectionMNIST classifiers · MNIST with simulated outliersprecision-recall curve performanceImproved
Use the proposed FI measure instead of the Jacobian norm for simulated-outlier detectionMNIST classifiers · MNIST with simulated outliersROC curve performanceNo clear effect
Choose DenseNet121 rather than ResNet50CIFAR10 classifiers · CIFAR10FI: 2.87e-3 -> 1.10e-4 (75th percentile, training); 0.031 -> 1.83e-3 (75th percentile, test)Improved
Choose DenseNet121 rather than ResNet50CIFAR10 classifiers · CIFAR10test accuracy: 88.70% -> 91.16%Improved
Choose DenseNet121 rather than ResNet50MNIST classifiers · MNISTFIMixed
Use multi-scale pixel neighborhoods rather than only a single pixel scaleFI-based vulnerable-region detection · CIFAR10 and MNIST test imagesvulnerable-region coverageMixed

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