AI Paper Atlas

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

Breaking Temporal Consistency: Generating Video Universal Adversarial Perturbations Using Image Models

Hee-Seon Kim, Minji Son, Minbeom Kim, Myung-Joon Kwon, Changick Kim

ICCV 2023 · Adversarial robustness and security › Attacks on text and graphs · approach: Adversarial perturbations beyond images · 11 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 Temporal Similarity Loss (BTC) to image-model UAP optimization, versus I2V-UAPRes-101 UAP, ImageNet · Kinetics-400, avg over 6 video modelsASR (%): 65.90 -> 79.31Improved
add Temporal Similarity Loss (BTC) versus I2V-UAP with UCF-101 source dataRes-101 UAP · UCF-101 unseen group, avg over 6 video modelsASR (%): 28.56 -> 51.12Improved
generate UAP from image model and image data (BTC) instead of video models and dataBTC-UAP · Kinetics-400, avg ASRASR (%): 70.88 (TT-UAP SF-101) -> 79.31Improved
use BTC-UAP with VGG16 source model instead of I2V-UAPVGG16 UAP · Kinetics-400, avgASR (%): 52.06 -> 73.41Improved
use BTC-UAP with SqueezeNet source model instead of the best baselineSqueezeNet UAP · Kinetics-400, avgASR (%): 59.99 -> 64.83Improved
add Feature Diversity with K=4 random noises (ablation)BTC-UAP adversarial loss · UCF-101ASR (%)Improved
use neighbor distance set J={-2,-1,1,2} instead of smaller sets (ablation)BTC-UAP temporal loss · UCF-101ASR (%)Improved
use temporal loss J={-1,1} with K=4 instead of K=6 at same compute (ablation)BTC-UAP · UCF-101ASR (%)Improved
reduce number of UAP frames N from 32 to 2 (repeated) (ablation)BTC-UAP · UCF-101ASR (%)No clear effect
shift the UAP along the temporal axis by 1 to 8 frames (ablation)BTC-UAP · UCF-101ASR (%)No clear effect
repeat 32-frame UAP to cover 64-frame Kinetics videos without re-optimizingBTC-UAP · Kinetics-400ASR (%)No clear effect

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