AI Paper Atlas

Research map / Adversarial robustness and security / Black-box and transfer attacks

Consistency-Sensitivity Guided Ensemble Black-Box Adversarial Attacks in Low-Dimensional Spaces

Jianhe Yuan, Zhihai He

ICCV 2021 · Adversarial robustness and security › Black-box and transfer attacks · approach: Query-efficient black-box attacks · 5 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 sensitivity-guided local refinement after direct transfer attack (ablation)CSEA, ResNet victim · CIFAR-10 untargetedsuccess rate: 90.9% -> 100.0%Improved
add sensitivity-guided local refinement after direct transfer attack (ablation)CSEA, DenseNet victim · CIFAR-10 untargetedsuccess rate: 96.1% -> 100.0%Improved
order block flips by sensitivity map instead of random order (ablation)local block refinement · CIFAR-10 untargetedmean queries: 140.7 -> 113.3Improved
let the attacker keep memory of queries from earlier imagesCSEA, ResNet victim · CIFAR-10 untargetedmean queries: 74.2 -> 43.2Improved
let the attacker keep memory of queries from earlier imagesCSEA, DenseNet victim · CIFAR-10 untargetedmean queries: 65.4 -> 11.4Improved
let the attacker keep memory of queries from earlier imagesCSEA, ResNet victim · CIFAR-10 targetedmean queries: 930.4 -> 860.4Improved
use CSEA instead of Subspace AttackSubspace Attack · ImageNet SENet untargetedmean queries: 456 -> 360Improved
use CSEA instead of Subspace AttackSubspace Attack · ImageNet PNAS-Net untargetedmean queries: 680 -> 398Improved
use CSEA instead of Subspace AttackSubspace Attack · ImageNet Inception-v3 untargetedfailure rate: 1.1% -> 1.8%Hurt
use CSEA instead of NP-AttackNP-Attack · CIFAR-10 targeted, ResNet victimmean queries: 936 -> 930.4No clear effect
use CSEA instead of SimBASimBA · CIFAR-10 untargeted, ResNet victimmean queries: 432.1 -> 74.2Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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