AI Paper Atlas

Research map / Federated learning and privacy / Privacy attacks and secure learning

Learning a Dynamic Privacy-preserving Camera Robust to Inversion Attacks

Jiacheng Cheng, Xiang Dai, Jia Wan, Nick Antipa, Nuno Vasconcelos

ECCV 2024 · Federated learning and privacy › Privacy attacks and secure learning · approach: Visual privacy and face de-identification · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use a dynamic (randomly sampled) PSF so attackers cannot recover it, versus static PSF under white-box inversionDyPP camera · PubFig face recognition after TVD attackaccuracy: 54% (white-box) -> 14% (black-box)Improved
PSF inversion with true PSF instead of blind or deep-learning deblurringstatic-PSF cameras · Reconstruction PSNR/SSIMPSNR: from ~15 to ~20 PSNR, ~0.55 to ~0.75 SSIMImproved
DyPP versus PP-HPE lens on object detectionDyPP · COCO Detection valAP: 33.9 -> 36.0Improved
DyPP versus PP-HPE lens on pose estimationDyPP · COCO Keypoints valAP: 42.8 -> 42.2No clear effect
DyPP versus PP-HPE lens on crowd countingDyPP · ShanghaiTech BMAE: 21.3 -> 19.3Improved
use extremely low-resolution sensor for privacyLow-resolution camera · COCO pose / detectionAP: pose AP 10.3 vs 42.2 for DyPPHurt
black-box attack with 64 sampled PSFs instead of white-boxDyPP · Reconstruction PSNRPSNR: 20.3 -> 17.3Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy