AI Paper Atlas

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

Sparse Black-Box Video Attack with Reinforcement Learning

Xingxing Wei, Huanqian Yan, Bo Hu Li

IJCV 2022 · Adversarial robustness and security › Black-box and transfer attacks · approach: Query-efficient black-box attacks · 56 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 RL key-frame agent with R_attack reward to FGSM+NES (ablation)SVA · un-targeted attack, 20 UCF-101 videosMAP: 6.5037 -> 2.3723Improved
add R_rep reward to R_attack (ablation)SVA · un-targeted attack, 20 UCF-101 videosMAP: 2.3723 -> 2.0321Improved
add R_div reward on top of R_attack and R_rep (ablation)SVA · un-targeted attack, 20 UCF-101 videosMAP: 2.0321 -> 1.8624Improved
add RL agent (sparsity) vs no RL (ablation)SVA · un-targeted attack, 20 UCF-101 videossparsity (%): 0.00 -> 62.35Improved
add R_rep and R_div to R_attack (ablation)SVA · un-targeted attack, 20 UCF-101 videossparsity (%): 62.35 -> 74.65Improved
replace random keyframe selection with RL agent (ablation)SVA · C3D, UCF101 20 videosfooling rate, query, MAPImproved
replace Heuristic-attack keyframe selection with proposed RL selection (SVA_opt) (ablation)Heuristic-attack · C3D, UCF-101 and HMDB-51MAP, Q, S, FRImproved
swap NES gradient estimator for SignSGD (ablation)SVA · C3D, UCF101 20 videosfooling rate: 10% better fooling rateMixed
swap NES gradient estimator for Sign-OPT (ablation)SVA · C3D, UCF101 20 videosfooling rate: 5% better fooling rateMixed
increase sparsity of SVAL from 50% to 70% (ablation)SVAL · C3D UCF-101 un-targeted, 10 videosfooling rate (%): 100.00 -> 60.0Hurt
use SVA instead of SVAL on HMDB-51 LRCN un-targetedSVA · HMDB-51 LRCN un-targetedMAP: 1.9479 -> 3.1570Hurt
use SVA instead of Heuristic-attack in targeted modeSVA · UCF-101 targetedfooling rate: - -> 32.0Improved

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