AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

Degraded Polygons Raise Fundamental Questions of Neural Network Perception

Leonard Tang, Dan Ley

NeurIPS 2023 · Adversarial robustness and security › Attacks on text and graphs · approach: Biologically inspired robust vision · 0 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 ImageNet rather than FractalDB pretrainingResNet-18 · Pentagon, 0.5 Corner Degradationper-class accuracy (%): 100.0 -> 0.1Hurt
Use FractalDB rather than ImageNet pretrainingResNet-18 · Pentagon, 0.5 Edge Degradationper-class accuracy (%): 0.0 -> 2.4Improved
Degrade polygon edges rather than cornersImageNet-pretrained ResNet-18 · Pentagon, 0.5 degradationper-class accuracy (%): 0.1 -> 0.0No clear effect
Degrade polygon edges rather than cornersFractalDB-pretrained ResNet-18 · Pentagon, 0.5 degradationper-class accuracy (%): 100.0 -> 2.4Hurt
Increase perimeter degradationVision architectures · Degraded regular polygonstop-1 test accuracyHurt
Use FractalDB rather than ImageNet pretrainingResNet-18 and ResNet-50 · Degraded regular polygonstop-1 test accuracyMixed
Use ResNet-18, ResNet-50, or MLP-Mixer instead of ViTImageNet-pretrained models · Edge- versus corner-degraded polygonstop-1 test accuracyMixed

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