CityGuard: Graph-Aware Private Descriptors for Bias-Resilient Identity Search Across Urban Cameras

TL;DR

CityGuard introduces a privacy-preserving, graph-aware transformer framework for robust urban person re-identification across cameras, addressing appearance changes and domain shifts with differential privacy.

Contribution

It proposes a novel topology-aware transformer with adaptive metric learning and geometry-conditioned attention for privacy-preserving, bias-resilient identity search in decentralized surveillance.

Findings

Achieves higher retrieval precision on Market-1501 and other benchmarks.

Supports secure, cost-efficient deployment with differential privacy.

Demonstrates robustness to viewpoint, occlusion, and domain shifts.

Abstract

City-scale person re-identification across distributed cameras must handle severe appearance changes from viewpoint, occlusion, and domain shift while complying with data protection rules that prevent sharing raw imagery. We introduce CityGuard, a topology-aware transformer for privacy-preserving identity retrieval in decentralized surveillance. The framework integrates three components. A dispersion-adaptive metric learner adjusts instance-level margins according to feature spread, increasing intra-class compactness. Spatially conditioned attention injects coarse geometry, such as GPS or deployment floor plans, into graph-based self-attention to enable projectively consistent cross-view alignment using only coarse geometric priors without requiring survey-grade calibration. Differentially private embedding maps are coupled with compact approximate indexes to support secure and cost-efficient deployment. Together these designs produce descriptors robust to viewpoint variation, occlusion, and domain shifts, and they enable a tunable balance between privacy and utility under rigorous differential-privacy accounting. Experiments on Market-1501 and additional public benchmarks, complemented by database-scale retrieval studies, show consistent gains in retrieval precision and query throughput over strong baselines, confirming the practicality of the framework for privacy-critical urban identity matching.