AI Paper Atlas

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

FeatureFool: Zero-Query Fooling of Video Models via Feature Map

Duoxun Tang, Xi Xiao, Guangwu Hu, Kangkang Sun, Xiao Yang, Dongyang Chen, Qing Li, Yong-jie Yin, Jiyao Wang

CVPR 2026 · Adversarial robustness and security › Black-box and transfer attacks · approach: Robustness benchmarks and defenses · 0 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
use max-optical-flow frame instead of a random frame for the feature map (ablation)FeatureFool (C3D) · UCF-101ASR: 53% -> 70%Improved
use max-optical-flow frame instead of a random frame for the feature map (ablation)FeatureFool (I3D) · UCF-101ASR: 57% -> 74%Improved
single max-flow frame instead of computing feature map on every frame (ablation)FeatureFool (C3D) · UCF-101ASR: 65% -> 70%Improved
single max-flow frame instead of computing feature map on every frame (ablation)FeatureFool (I3D) · UCF-101ASR: 70% -> 74%Improved
select attack video by SSIM or cosine similarity instead of random (ablation)FeatureFool · UCF-101/HMDB-51/Kinetics-400ASR: about 70% in all casesNo clear effect
use feature map from a different source architecture (ablation)FeatureFool · UCF-101ASR: 70.0% -> 66.0% (C3D source to I3D victim)Hurt
use feature map from a different source dataset (ablation)FeatureFool · UCF-101ASR: 70.0% -> 68.0% (C3D-UCF-101 source to HMDB-51 victim)Hurt
increase injection strength alpha from 0.1 to 1.0 (ablation)FeatureFool (C3D) · HMDB-51ASR / SSIM / PSNRMixed
use raw Guided Back-propagation feature map instead of FullGrad or Grad-Cam (ablation)FeatureFool · UCF-101ASR and qualityImproved
replace query-based attack with zero-query feature map attackFeatureFool vs BSC · Kinetics-400 (C3D)ASR: 76% -> 70%Hurt
replace baselines with FeatureFool on Video-LLMsFeatureFool vs BSC · Video-LLM harmful clipsASR: 35.00% -> 76.25%Improved
apply FeatureFool under TS defenseFeatureFool vs PatchAttack · UCF-101 (C3D)Residual-ASR: 55.0% -> 66.0%Improved

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