# PPEDCRF: Dynamic-CRF-Guided Selective Perturbation for Background-Based Location Privacy in Video Sequences

arXiv: https://arxiv.org/abs/2604.17163 · HTML: https://mlsanity.com/paper/2604.17163/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 41 references that are in the map.
- First posted on arXiv 18 Apr 2026.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Renyi Differential Privacy](https://mlsanity.com/paper/1702.07476/) (2017)
- [Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition](https://mlsanity.com/paper/2103.01486/) (2021)
- [Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising](https://mlsanity.com/paper/1805.06530/) (2018)
- [Conditional Random Fields as Recurrent Neural Networks](https://mlsanity.com/paper/1502.03240/) (2015)
- [CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks](https://mlsanity.com/paper/2005.09544/) (2020)
- [Revealing Scenes by Inverting Structure from Motion Reconstructions](https://mlsanity.com/paper/1904.03303/) (2019)
- [Learning to Anonymize Faces for Privacy Preserving Action Detection](https://mlsanity.com/paper/1803.11556/) (2018)
- [Natural and Effective Obfuscation by Head Inpainting](https://mlsanity.com/paper/1711.09001/) (2017)
- [Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study](https://mlsanity.com/paper/1807.08379/) (2018)
- [Mitigating Information Leakage in Image Representations: A Maximum Entropy Approach](https://mlsanity.com/paper/1904.05514/) (2019)
- [Privacy Preserving Image-Based Localization](https://mlsanity.com/paper/1903.05572/) (2019)
- [Defeating Image Obfuscation with Deep Learning](https://mlsanity.com/paper/1609.00408/) (2016)
- [Privacy Preserving Face Recognition Utilizing Differential Privacy](https://mlsanity.com/paper/2005.10486/) (2020)
- [Faceless Person Recognition; Privacy Implications in Social Media](https://mlsanity.com/paper/1607.08438/) (2016)
- [Personal Privacy Protection via Irrelevant Faces Tracking and Pixelation in Video Live Streaming](https://mlsanity.com/paper/2101.01060/) (2021)

## Abstract (arXiv)

We propose PPEDCRF, a calibrated selective perturbation framework that protects background-based location privacy in released video frames against gallery-based retrieval attackers. Even after GPS metadata are stripped, an adversary can geolocate a frame by matching its background visual cues to geo-tagged reference imagery; PPEDCRF mitigates this threat by estimating location-sensitive background regions with a dynamic conditional random field (DCRF), rescaling perturbation strength with a normalized control penalty (NCP), and injecting Gaussian noise only inside the inferred regions via a DP-style calibration rule. On a controlled paired-scene retrieval benchmark with eight attacker backbones and three noise seeds, PPEDCRF reduces ResNet18 Top-1 retrieval accuracy from 0.667 to 0.361±0.127 at σ0=8 while preserving 36.14,dB PSNR -- an ≈6,dB quality advantage over global Gaussian noise. Transfer across the eight-backbone seed-averaged benchmark is broadly supportive (23 of 24 backbone-gallery cells show negative Delta), while appendix-scale confirmation identifies MixVPR as a remaining adverse-transfer exception. Matched-operating-point analysis shows that PPEDCRF and global Gaussian noise converge in Top-1 privacy at equal utility, so the practical benefit is spatially concentrated perturbation that preserves higher visual quality at any given noise scale rather than stronger matched-utility privacy. Code: https://github.com/mabo1215/PPEDCRF