AI Paper Atlas

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

Universal Perturbation Attack Against Image Retrieval

Jie Li, Rongrong Ji, Hong Liu, Xiaopeng Hong, Yue Gao, Qi Tian

ICCV 2019 · Adversarial robustness and security › Attacks on text and graphs · approach: Adversarial perturbations beyond images · 120 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 pair-wise ranking relationship instead of label-wise classification-style lossUAP against retrieval · V-MAC retrievalmean dropping rate (mDR): 61.80% -> 66.94%Improved
use pair-wise instead of label-wise lossUAP against retrieval · R-GeM retrievalmean dropping rate (mDR): 23.76% -> 66.69%Improved
add list-wise (NDCG-based) relationship on top of pair-wise (ablation)UAP against retrieval · A-MAC retrievalmean dropping rate (mDR): 44.35% -> 48.33%Improved
add list-wise relationship on top of pair-wise (ablation)UAP against retrieval · R-MAC retrievalmean dropping rate (mDR): 59.71% -> 62.60%Improved
add list-wise relationship on top of pair-wise (ablation)UAP against retrieval · V-MAC retrievalmean dropping rate (mDR): 66.94% -> 67.96%Improved
use ranking-distilled substitute model instead of ImageNet pre-trained model for black-box attack (ablation)UAP against retrieval · A-GeMmean dropping rate (mDR): 32.98% -> 39.72%Improved
use ranking-distilled substitute model instead of ImageNet pre-trained model (ablation)UAP against retrieval · V-GeMmean dropping rate (mDR): 28.85% -> 44.68%Improved
use ranking-distilled model instead of randomly initialized model (ablation)UAP against retrieval · A-GeMmean dropping rate (mDR): 5.53% -> 39.72%Improved
use multi-scale random resizing [256,1024] instead of fixed 362x362 (ablation)list-wise UAP · A-GeMmean dropping rate (mDR): 16.89% -> 56.88%Improved
use multi-scale random resizing [256,1024] instead of fixed 1024x1024 (ablation)list-wise UAP · V-GeMmean dropping rate (mDR): 30.42% -> 63.72%Improved
narrow the random resizing range from [256,1024] to [768,1024] (ablation)list-wise UAP · V-GeMmean dropping rate (mDR): 63.72% -> 42.08%Hurt
widen the random resizing range from [256,1024] to [128,1024] (ablation)list-wise UAP · A-GeMmean dropping rate (mDR): 56.88% -> 53.21%Hurt

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