PPEDCRF: Privacy-Preserving Enhanced Dynamic CRF for Location-Privacy Protection for Sequence Videos with Minimal Detection Degradation

TL;DR

PPEDCRF is a novel framework that enhances location privacy in dashcam videos by selectively perturbing background regions while preserving detection accuracy, effectively resisting background-based retrieval attacks.

Contribution

It introduces a dynamic CRF with hierarchical sensitivity-based noise injection to protect location privacy without degrading foreground detection performance.

Findings

Significantly reduces location-retrieval attack success rates.

Maintains high object detection and segmentation performance.

Outperforms baseline privacy-preserving methods in experiments.

Abstract

Dashcam videos collected by autonomous or assisted-driving systems are increasingly shared for safety auditing and model improvement. Even when explicit GPS metadata are removed, an attacker can still infer the recording location by matching background visual cues (e.g., buildings and road layouts) against large-scale street-view imagery. This paper studies location-privacy leakage under a background-based retrieval attacker, and proposes PPEDCRF, a privacy-preserving enhanced dynamic conditional random field framework that injects calibrated perturbations only into inferred location-sensitive background regions while preserving foreground detection utility. PPEDCRF consists of three components: (i) a dynamic CRF that enforces temporal consistency to discover and track location sensitive regions across frames, (ii) a normalized control penalty (NCP) that allocates perturbation strength according to a hierarchical sensitivity model, and (iii) a utility-preserving noise injection module that minimizes interference to object detection and segmentation. Experiments on public driving datasets demonstrate that PPEDCRF significantly reduces location-retrieval attack success (e.g., Top-k retrieval accuracy) while maintaining competitive detection performance (e.g., mAP and segmentation metrics) compared with common baselines such as global noise, white-noise masking, and feature-based anonymization. The source code is in https://github.com/mabo1215/PPEDCRF.git