AI Paper Atlas

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

Prompt-driven Transferable Adversarial Attack on Person Re-Identification with Attribute-aware Textual Inversion

Yuan Bian, Min Liu, Yunqi Yi, Xueping Wang, Shuai Jiang, Yaonan Wang

ICCV 2025 · Adversarial robustness and security › Attacks on text and graphs · approach: Vision-language model robustness · 1 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 global CLIP visual feature loss to surrogate feature loss (ablation)AP-Attack generator · Cross-model&dataset attackaAP: 45.8 -> 27.9Improved
add integral text embedding loss instead of global visual feature (ablation)AP-Attack generator · Cross-model&dataset attackaAP: 27.9 -> 25.9Improved
add fine-grained attribute semantic loss instead of integral text embedding (ablation)AP-Attack generator · Cross-model&dataset attackaAP: 25.9 -> 21.2Improved
add fine-grained attribute semantic loss (mDR view) (ablation)AP-Attack generator · Cross-model&dataset attackmDR: 40.3 -> 72.4Improved
use AP-Attack instead of PDCL-AttackAP-Attack · Cross-model&dataset attackaAP: 38.7 -> 21.2Improved
use AP-Attack instead of PDCL-AttackAP-Attack · Cross-model attackaAP: 19.0 -> 6.9Improved
use AP-Attack instead of PDCL-AttackAP-Attack · Cross-dataset attackaAP: 6.6 -> 5.7Improved
compare AP-Attack with multi-dataset MetaAttackAP-Attack · Cross-dataset attackaAP: 5.7 -> 3.7Hurt
use AP-Attack instead of Mis-Ranking against defensesAP-Attack · Defense evaluationaAP: 50.2 -> 31.1Improved
attack unseen model types with AP-AttackAP-Attack · PASS (Market) mAPmAP: 92.2 -> 12.1Improved
attack CLIP-ReID victim with AP-AttackAP-Attack · CLIP-ReID (Market) mAPmAP: 89.6 -> 32.7Improved

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