cs.CVSep 26, 2024

Transferable Multiform Attack for Cross-Modal Person Re-Identification

Authors: Yunpeng Gong, Can Yang, Qingyuan Zeng, Dejun Xu, Zhiming Luo, Zhenzhong Wang, Min Jiang

Organizations: School of Informatics, Xiamen University · Department of Computing, The Hong Kong Polytechnic University

Abstract

Cross-modal person re-identification (ReID) adversarial attacks face a transferability challenge: existing methods may exhibit source-pair overfitting, where learned perturbations become overly dependent on the feature statistics of the source modality pair, thereby limiting their transferability under heterogeneous domain shifts. We argue that a key challenge is reducing source-pair-specific bias while maintaining attack effectiveness. To address this, we propose Multiform Attack (MA). The framework first learns a universal perturbation via Mahalanobis-guided gradient optimization. Since this perturbation may still retain source-pair-specific bias, the second stage performs sparse refinement through attention-shift-filtered multi-objective evolutionary search, leveraging heterogeneous source distributions in transfer settings. By separating universal perturbation learning from sparse evolutionary refinement, MA aims to reduce reliance on source-pair-specific patterns and improve transferability to unseen domains. Extensive experiments demonstrate strong attack effectiveness on cross-modal ReID benchmarks and improved transferability in the evaluated held-out-domain settings, with additional evaluations across model architectures.

Figures & tables

Explore similar work

CardsList
  1. AIDA-ReID: Adaptive Intermediate Domain Adaptation for Generalizable and Source-Free Person Re-Identification

    Apr 30, 2026Sundas Iqbal, Qing Tian, Danish Ali +2Multi-Source Domain AdaptationSource-Free Domain Adaptation

  2. Dual-Space Modality Consistency Learning for Universal Cross-Modal Re-Identification

    Aug 7, 2026Yujian Zhao, Yukang Zhao, Hankun Liu +4Cross-Modal AlignmentMultimodal Contrastive Learning

  3. MDA framework: multi-architecture domain adaptation for unsupervised person re-identification

    Nov 9, 2026Wei Zhang, Peijun Ye, Dihu Chen +1Person Re-IdentificationUnsupervised Domain Adaptation