AI Paper Atlas

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

Effective and Efficient Vote Attack on Capsule Networks

Jindong Gu, Baoyuan Wu, Volker Tresp

ICLR 2021 · Adversarial robustness and security › Certified and empirical robustness · approach: Attack evaluation and defense critique · 12 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
Attack votes directly instead of output capsulesCapsNet with PGD · CIFAR10robust accuracy: 17.3{ ($\pm$1.35)} -> 4.83{ ($\pm$0.05)}Improved
Attack votes directly instead of output capsulesCapsNet with PGD · SVHNrobust accuracy: 34.82{ ($\pm$2.11)} -> 8.11{ ($\pm$0.3)}Improved
Add Vote-Attack examples to adversarial trainingCapsNet · CIFAR10robust accuracy (PGD): 43.65{ ($\pm$0.85)} -> 44.12{ ($\pm$0.32)}; 45.49{ ($\pm$0.78)} -> 49.62{ ($\pm$0.56)}Mixed
Add Vote-Attack examples to adversarial trainingCapsNet · SVHNrobust accuracy (PGD): 30.44{ ($\pm$1.08)} -> 34.92{ ($\pm$0.98)}; 33.40{ ($\pm$1.36)} -> 39.13{ ($\pm$0.96)}Mixed
Remove output-capsule routing from attack computation by attacking votesCapsNet PGD attack · CIFAR10 testattack time: 471.81\textit{ms} -> 414.58\textit{ms}Improved
Integrate Vote-Attack into detection-aware attackCapsNet · FMNISTundetected rate (PGD): 78.2 -> 86.1Improved
Use Vote-Attack instead of Caps-Attack to create targeted examplesCapsNet with PGD · CIFAR10targeted attack success rate: 65.94{ ($\pm$0.92)} -> 75.35{ ($\pm$0.91)}Improved
Generate examples by attacking votes rather than output capsulesCapsNet with PGD · CIFAR10transfer success rate to CapsNet: 46.43{ ($\pm$5.56)} -> 55.34{ ($\pm$6.26)}Improved
Squash each vote before averaging (ablation)Vote-Attack · CIFAR10robust accuracy (PGD): 4.83{ ($\pm$0.05)} -> 4.06{ ($\pm$1.12)}No clear effect
Average individual-vote losses instead of loss on the squashed averaged vote (ablation)Vote-Attack · CIFAR10robust accuracy (PGD): 4.83{ ($\pm$0.05)} -> 43.31{ ($\pm$2.46)}Hurt
Train using Vote-Attack examples aloneCapsNet adversarial training · CIFAR10 and SVHNrobust accuracyHurt

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