AI Paper Atlas

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

Neural Population Geometry Reveals the Role of Stochasticity in Robust Perception

Joel Dapello, Jenelle Feather, Hang Le, Tiago Marques, David Daniel Cox, Josh Mcdermott, James J. DiCarlo, SueYeon Chung

NeurIPS 2021 · Adversarial robustness and security › Certified and empirical robustness · approach: Attack evaluation and defense critique · 6 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
add Gaussian noise with σ=0.125 at the cochleagram representation (ablation)StochCochResNet50 · Word-Speaker-Noise held-out speech, L∞ attacksadversarial performanceImproved
add inference-time stochasticity (ablation)StochCochResNet50 · Word-Speaker-Noise held-out speech, L∞ attacksadversarial robustnessImproved
add inference-time stochasticity (ablation)StochCochResNet50 · Word-Speaker-Noise held-out speech, L2 attacksadversarial robustnessImproved
replace Poisson-like noise with Gaussian noise (ablation)VOneResNet50 · ImageNet validation, L∞ PGDadversarial robustnessNo clear effect
increase Gaussian noise level (ablation)CIFAR-VOneNet · CIFAR-10 class and exemplar manifoldsmanifold capacityHurt
increase Gaussian noise level (ablation)CIFAR-VOneNet · CIFAR-10 clean and adversarial exemplar manifoldsmanifold overlapHurt
increase Gaussian noise level (ablation)StochCochResNet50 · Word-Speaker-Noise class and adversarial exemplar manifoldsmanifold capacityHurt
increase Poisson noise ratio (ablation)CIFAR-10 VOneNet · CIFAR-10 adversarial performanceadversarial performanceMixed
replace Gaussian noise with Poisson-like noise (ablation)CIFAR-VOneNet · CIFAR-10 adversarial performance across attack strengthsadversarial performanceImproved
adversarially train the model (ablation)CochResNet50 · Word-Speaker-Noise, L2 attacksadversarial robustnessImproved
increase Gaussian noise level (ablation)CIFAR-VOneNet · CIFAR-10 VOneBlock stochastic layermanifold widthHurt
use random shell perturbations instead of FGSM perturbations to sample exemplar manifolds (ablation)VOneNets · ImageNet exemplar manifoldsmanifold capacity trendsNo 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