AI Paper Atlas

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

Spatial-frequency channels, shape bias, and adversarial robustness

Ajay Subramanian, Elena Sizikova, Najib J. Majaj, Denis G. Pelli

NeurIPS 2023 · Adversarial robustness and security › Attacks on text and graphs · approach: Latency and driving-perception attacks · 3 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 a narrower channel bandwidthNeural networks evaluated on 16-way ImageNet categorization · 16-way ImageNet cue-conflict categorizationshape bias: 29%Improved
Increase channel bandwidth and peak noise sensitivityAdversarially trained networks · ImageNet validation with PGD whitebox attackwhitebox accuracy: 66% variance explained by the three channel properties togetherImproved
Increase the amount of adversarial trainingResNet-50 · ImageNet validation with PGD whitebox attackwhitebox accuracyImproved
Increase the amount of adversarial trainingResNet-50 · ImageNet validation setaccuracyHurt
Increase the amount of adversarial trainingResNet-50 · 16-way ImageNet categorization with narrowband noisechannel bandwidthHurt
Use more than a one-octave-wide channelNeural networks · 16-way ImageNet categorization with narrowband noisechannel bandwidth: 2.30 to 5.98, compared with 1.00 octaveHurt
Use a weaker PGD evaluation attack, 20-step PGD with ||L∞||=4/255Adversarially trained networks · ImageNet validation whitebox robustnesscorrelation between channel bandwidth and whitebox accuracyNo 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