AI Paper Atlas

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

Guessing Smart: Biased Sampling for Efficient Black-Box Adversarial Attacks

Thomas Brunner, Frederik Diehl, Michael Truong Le, Alois Knoll

ICCV 2019 · Adversarial robustness and security › Black-box and transfer attacks · approach: Query-efficient black-box attacks · 124 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 Perlin low-frequency bias (ablation)Boundary Attack · ImageNet targeted attacksuccess rate at 15000 queries: 0.33 -> 0.57Improved
add regional mask bias (ablation)Boundary Attack · ImageNet targeted attacksuccess rate at 15000 queries: 0.33 -> 0.44Improved
add surrogate gradient bias (ablation)Boundary Attack · ImageNet targeted attacksuccess rate at 15000 queries: 0.33 -> 0.38Improved
add mask bias to Perlin-biased attack (ablation)Boundary Attack + Perlin · ImageNet targeted attacksuccess rate at 15000 queries: 0.57 -> 0.80Improved
add surrogate gradient bias to Perlin+mask attack (ablation)Boundary Attack + Perlin + Mask · ImageNet targeted attacksuccess rate at 15000 queries: 0.80 -> 0.85Improved
add surrogate gradient bias to Perlin-biased attack (ablation)Boundary Attack + Perlin · ImageNet targeted attacksuccess rate at 15000 queries: 0.57 -> 0.60Improved
add surrogate gradient bias to mask-biased attack (ablation)Boundary Attack + Mask · ImageNet targeted attacksuccess rate at 15000 queries: 0.44 -> 0.49Improved
add surrogate gradient bias to Perlin+mask attack (ablation)Boundary Attack + Perlin + Mask · ImageNet targeted attackmedian queries until success: 5485 -> 5432Improved
add Perlin bias to random guessing (ablation)Random guessing · Tiny ImageNet AVC untargetedmedian L2 distance: 11.15 -> 4.28Improved
add Perlin bias to Boundary Attack (ablation)Boundary Attack · Tiny ImageNet AVC targetedmedian L2 distance: 20.2 -> 15.1Improved
add surrogate gradients to Perlin-biased attack (ablation)Boundary Attack + Perlin · Tiny ImageNet AVC targetedmedian L2 distance: 15.1 -> 9.5Improved
replace unbiased Boundary Attack with Biased Boundary AttackBoundary Attack · ImageNet targeted attack vs other label-only attackssuccess rate at 15000 queries: 0.33 -> 0.85Improved

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