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

2026-02-20

AI Summary

This work addresses the challenges of city-scale cross-camera person re-identification, where drastic appearance variations arise from viewpoint changes, occlusions, and domain shifts, compounded by privacy constraints that prohibit sharing raw images. To tackle these issues, we propose a topology-aware decentralized Transformer framework that integrates graph-structured spatially conditioned self-attention, feature-dispersed adaptive metric learning, and differentially private embedding coupled with compact approximate indexing. Leveraging only coarse geometric priors, our method achieves cross-view identity alignment while preserving privacy. Experiments demonstrate that the proposed framework significantly improves retrieval accuracy and query throughput on benchmarks such as Market-1501, achieving a tunable trade-off between utility and security without compromising data privacy.

Technology Category

• Machine Learning: Privacy
• Computer Vision: Bias, Fairness & Privacy
• Search and Optimization: Distributed Search

Application Category

• Security and Privacy: Privacy-enhancing technologies
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Responsible Web: Data and user privacy-enhancing technologies for the Web

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.

Problem

• person re-identification
• privacy-preserving
• urban surveillance
• appearance variation
• data protection

Innovation

• dispersion-adaptive metric learning
• spatially conditioned attention
• differentially private embedding
• graph-aware transformer
• privacy-preserving re-identification