Revisiting Geometric Obfuscation with Dual Convergent Lines for Privacy-Preserving Image Queries in Visual Localization

2026-04-24

AI Summary

This work addresses the vulnerability of existing geometry-based image query privacy-preserving methods, which remain susceptible to attacks due to residual geometric cues—specifically, blurred neighboring lines that can still reveal the original keypoint locations. To mitigate this, the authors propose Dual Convergent Lines (DCL), a novel approach that maps each keypoint onto lines emanating from one of two fixed anchor points placed on a central bisecting line. This design deliberately disrupts the recoverability of the original geometric structure, rendering the attacker’s optimization problem ill-posed: reconstructed lines either erroneously converge to a single anchor or become nearly parallel near image boundaries, yielding high-variance, unstable solutions. DCL seamlessly integrates with existing line-based solvers and fits naturally into conventional visual localization pipelines. Extensive experiments demonstrate that DCL achieves strong privacy robustness, computational efficiency, and scalability across large-scale indoor and outdoor datasets while preserving practical localization accuracy.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Privacy
• Search and Optimization: Local Search

Application Category

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

Abstract

Privacy-Preserving Image Queries (PPIQ) are an emerging mechanism for cloud-based visual localization, enabling pose estimation from obfuscated features instead of private images or raw keypoints. However, the main approaches for PPIQ, primarily geometry-based and segmentation-based obfuscation, both suffer from vulnerabilities to recent privacy attacks. In particular, a fundamental limitation of geometry-based obfuscation is that the spatial distribution of obfuscated neighboring lines still effectively surrounds the original keypoint location, providing exploitable cues for recovering the original points. We revisit this geometric paradigm and introduce Dual Convergent Lines (DCL), a novel keypoint obfuscation method demonstrating strong resilience against such attack. DCL places two fixed anchors on a central partition line and lifts each keypoint to a line originating from one of them, with the active anchor determined by the keypoint's location. This arrangement invalidates the geometry-recovery attack by making its optimization ill-posed: Neighboring lines either misleadingly converge to one anchor, yielding a trivial solution, or become near-parallel at the partition boundary, yielding an unstable high-variance solution. Both outcomes thwart point recovery. DCL is also compatible with an existing line-based solver, enabling deployment in traditional localization pipelines. Experiments on both indoor and large-scale outdoor datasets demonstrate DCL's robustness against privacy attacks, efficiency, and scalability, while achieving practical localization performance.

Problem

• Privacy-Preserving Image Queries
• Geometric Obfuscation
• Visual Localization
• Keypoint Recovery
• Privacy Attacks

Innovation

• Dual Convergent Lines
• Privacy-Preserving Image Queries
• Geometric Obfuscation
• Visual Localization
• Keypoint Privacy