AI Paper Atlas

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

CamoPatch: An Evolutionary Strategy for Generating Camoflauged Adversarial Patches

Phoenix Neale Williams, Ke Li

NeurIPS 2023 · Adversarial robustness and security › Attacks on text and graphs · approach: Adversarial perturbations beyond images · 1 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
remove simulated annealing from location optimization (random search) (ablation)CamoPatch · AT-WideResNet-50-2ASR: 87.02% -> 83.02%Hurt
remove simulated annealing from location optimization (ablation)CamoPatch · AT-ResNet-50ASR: 94.00% -> 90.00%Hurt
remove simulated annealing from location optimization (ablation)CamoPatch · VGG-16ASR: 90.30% -> 90.01No clear effect
remove simulated annealing from location optimization (ablation)CamoPatch · ResNet-50ASR: 90.00% -> 90.00%No clear effect
increase patch pattern optimization budget li from 1 to 4 (ablation)CamoPatch · VGG-16accuracy after attack: 12.88% -> 9.64%Improved
increase location exploration t from 100 to 300 (ablation)CamoPatch · VGG-16accuracy after attack: 10.79% -> 9.64%Improved
increase sigma from 0.1 to 0.3 (ablation)CamoPatch · VGG-16accuracy after attack: 9.64% -> 11.66%Hurt
increase number of circles N from 100 to 300 (ablation)CamoPatch · VGG-16accuracy and runtimeHurt
minimize l2 of patch in Patch-RS (Patch-RS*)Patch-RS · ImageNet classifierspatch l2 distance: 0.62 -> 0.42Improved
use circle-based RGB patch with arbitrary colors instead of corner-of-color-cube patchCamoPatch vs Patch-RS · ImageNet classifierspatch l2 distance: 0.71 -> 0.09Improved
adversarial training of classifierAT-ResNet-50 · ImageNetaccuracy after CamoPatch attack: 10.00% -> 6.00%Hurt
use WideResNet instead of ResNet in adversarial trainingAT classifier · ImageNetaccuracy after CamoPatch attack: 6.00% -> 12.98%Improved

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