Oriel — AI & technology worth noticing, every day.

Transferable Multiform Attack for Cross-Modal Person Re-Identification

Paper · https://arxiv.org/abs/2409.17977

arXiv:2409.17977v2 Announce Type: replace 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.

First seen by Oriel on .

No saved summary available.

Aliases

SourceExternal IDURL
arXiv AI Papersoai:arXiv.org:2409.17977v2https://arxiv.org/abs/2409.17977 Read discussion