AI Paper Atlas

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

Adversarial Attacks Are Reversible With Natural Supervision

Chengzhi Mao, Mia Chiquier, Hao Wang, Junfeng Yang, Carl Vondrick

ICCV 2021 · Adversarial robustness and security › Certified and empirical robustness · approach: Regularized defenses against attacks · 43 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 self-supervised reverse attack at inferenceSemi-SL · CIFAR-10 AutoAttackrobust accuracy: 60.22% -> 67.79%Improved
add self-supervised reverse attack at inferenceRO PreRes-18 · CIFAR-10 AutoAttackrobust accuracy: 48.95% -> 58.20%Improved
add self-supervised reverse attack at inferenceTRADES · CIFAR-10 PGD 50robust accuracy: 55.05% -> 57.00%Improved
add self-supervised reverse attack at inferenceAWP · CIFAR-10 BIM 200robust accuracy: 63.64% -> 63.69%Improved
add self-supervised reverse attack at inferenceRO ResNet18 · CIFAR-100 AutoAttackrobust accuracy: 19.23% -> 25.45%Improved
add self-supervised reverse attack at inferenceSemi-SL · SVHN AutoAttackrobust accuracy: 53.61% -> 65.50%Improved
add self-supervised reverse attack at inferenceFBF ResNet50 · ImageNet PGD10robust accuracy: 28.68% -> 31.36%Improved
add self-supervised reverse attack at inferenceMART · CIFAR-10 L2 C&W 200robust accuracy: 43.23% -> 45.85%Improved
increase defense-aware attacker's lambda_s from 0 to 10 (ablation)Ours vs Semi-SL/RO · CIFAR-10 PGD 50 adaptive attackrobust accuracy: lambda_s 0 to 10Mixed
use a random reverse perturbation instead of natural supervision (ablation)reverse defense · CIFAR-10 clean vs robust accuracyrobust accuracyHurt
increase number of reverse-attack iterations (ablation)Ours · CIFAR-10 accuracy vs time budgetrobust accuracyImproved
remove Gaussian blur from contrastive augmentations (ablation)contrastive branch G · CIFARrobust accuracyImproved

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