AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

AdvIT: Adversarial Frames Identifier Based on Temporal Consistency in Videos

Chaowei Xiao, Ruizhi Deng, Bo Li, Taesung Lee, Benjamin Edwards, Jinfeng Yi, Dawn Song, Mingyan Liu, Ian Molloy

ICCV 2019 · Adversarial robustness and security › Attacks on text and graphs · approach: Adversarial perturbations beyond images · 45 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 optical-flow pseudo frames with randomness instead of JPEG compressionAdvIT · Object detection (DAG Person)detection AUC: 60% -> 98%Improved
use optical-flow pseudo frames instead of replacing the frame with previous framesAdvIT · Segmentation (Houdini Stripe)detection AUC: 50% -> 100%Improved
use flow-warped pseudo frames instead of plain previous-frame replacementAdvIT · Object detection (DAG Person)detection AUC: 50% -> 98%Improved
aggregate more previous frames (k from 1 to 5)AdvIT · Object detection (DAG Person)detection AUC: 98% -> 100%Improved
aggregate more previous frames (k from 1 to 5)AdvIT · Sparse attack, action recognitiondetection AUC: 95% -> 97%Improved
aggregate more previous frames under adaptive attack with adversarial previous framesAdvIT · Adaptive attack, pose Shuffledetection AUC: 94% -> 100%Improved
aggregate more previous frames under adaptive attackAdvIT · Adaptive attack, segmentation ICCVdetection AUC: 95% -> 100%Improved
adaptive attacker using expectation over transformation versus non-adaptive attackAdvIT · Segmentation, pose, detectiondetection AUC: above 95%No clear effect
use a non-differentiable flow estimator against a differentiable-flow attackerAdvIT · Transferability (Table 3)detection AUC: 100%Improved
increase perturbation magnitude to 2, 16, 32 pixelsAdvIT · Perturbation strengthdetection rate: decrease a bitHurt
prior frames adversarial versus benignAdvIT · Segmentation, pose, detectiondetection AUC: almost 100%No clear effect
add detection with k pseudo-frame inferencesAdvIT · Segmentation run timeseconds: 2.58 -> 2.98Hurt

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