AI Paper Atlas

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

Multi-Expert Adversarial Attack Detection in Person Re-Identification Using Context Inconsistency

Xueping Wang, Shasha Li, Min Liu, Yaonan Wang, Amit K. Roy-Chowdhury

ICCV 2021 · Adversarial robustness and security › Attacks on text and graphs · approach: Defenses against universal perturbations · 43 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 more expert models (one to four) (ablation)MEAAD · Market1501detection F1: 95.5 -> 98.6Improved
add the attack target model to the other three experts (ablation)MEAAD · Market1501detection F1: 94.2 -> 98.6Improved
increase support set size from K=1 to K=15 (ablation)MEAAD · Market1501detection accuracy: 92.3 -> 98.5Improved
increase support set size beyond K=15 (ablation)MEAAD · Market1501detection accuracy: 98.5 -> 98.5No clear effect
add cross-expert affinity to query-support and support-support (ablation)MEAAD · Market1501detection F1: 97.0 -> 98.6Improved
add query-support affinity to cross-expert and support-support (ablation)MEAAD · Market1501detection F1: 95.7 -> 98.6Improved
add support-support affinity to cross-expert and query-support (ablation)MEAAD · Market1501detection F1: 97.1 -> 98.6Improved
replace threshold voting on common retrievals with a trained MLP detector (ablation)MEAAD · Market1501 (Deep Mis-Ranking)detection F1: 91.0 -> 98.6Improved
test detector on unseen Deepfool attack instead of the training attack CW (ablation)MEAAD · Market1501detection F1: 96.2 -> 95.9No clear effect
train detector on PGD and test on unseen CW attack (ablation)MEAAD · Market1501detection F1: 97.4 -> 93.8Hurt
adaptive CW attack with context-affinity loss term (target model white-box)MEAAD · Market1501detection accuracy: -1.3%Hurt
adaptive CW attack with context-affinity loss term (all models white-box)MEAAD · Market1501detection accuracy: -3.5%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