AI Paper Atlas

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

Query-Efficient Black-Box Adversarial Attacks Guided by a Transfer-Based Prior

Yinpeng Dong, Shuyu Cheng, Tianyu Pang, Hang Su, Jun Jie Zhu

TPAMI 2021 · Adversarial robustness and security › Black-box and transfer attacks · approach: Query-efficient black-box attacks · 67 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 transfer-based prior via biased samplingRGF · ImageNet l2 (Inception-v3)average queries: 1309 -> 745Improved
add transfer-based prior via gradient averagingRGF · ImageNet l2 (Inception-v3)average queries: 1309 -> 735Improved
use optimal lambda* instead of fixed lambda=0.05 (ablation)PRGF-BS · ImageNet l2 (Inception-v3)average queries: 1047 -> 745Improved
use optimal mu* instead of fixed mu=0.5 (ablation)PRGF-GA · ImageNet l2 (Inception-v3)average queries: 958 -> 735Improved
use optimal mu* instead of fixed mu=0.5 (ablation)PRGF-GA · CIFAR-10 l2 (ResNet-50)average queries: 306 -> 173Improved
add data-dependent priorPRGF-GA · ImageNet l2 (Inception-v3)average queries: 735 -> 644Improved
add data-dependent priorRGF · ImageNet l2 (Inception-v3)average queries: 1309 -> 910Improved
add data-dependent prior with three surrogate modelsPRGF-GA · ImageNet l2 (Inception-v3)average queries: 191 -> 267Hurt
use two surrogates with equal averaging instead of one (ablation)PRGF-GA · ImageNet l2 (Inception-v3)average queries: 735 -> 575Improved
use subspace projection instead of equal averaging for two surrogates (ablation)PRGF-GA · ImageNet l2 (Inception-v3)average queries: 575 -> 342Improved
add third surrogate Inception-ResNet-v2 (ablation)PRGF-GA · ImageNet l2 (Inception-v3)average queries: 342 -> 191Improved
use Inception-v4 instead of ResNet-v2-152 surrogate (ablation)PRGF-GA · ImageNet l2 (ResNet-50)average queries: 250 -> 350Hurt

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