AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Protecting Geolocation Privacy of Photo Collections

Jinghan Yang, Ayan Chakrabarti, Yevgeniy Vorobeychik

AAAI 2020 · Federated learning and privacy › Differential privacy · approach: Private data analysis frameworks · 6 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
Replace greedy photo deletion with optimal deletion selectionVGG-16 collection geolocation scores · R-16, top-1 guaranteefraction of photos deleted: 0.37 -> 0.32Improved
Replace greedy photo deletion with optimal deletion selectionVGG-16 collection geolocation scores · R-16, top-5 guaranteefraction of photos deleted: 0.53 -> 0.45Improved
Replace greedy photo deletion with optimal deletion selectionVGG-16 collection geolocation scores · R-32, top-1 guaranteefraction of photos deleted: 0.43 -> 0.31Improved
Replace greedy photo deletion with optimal deletion selectionVGG-16 collection geolocation scores · R-64, top-5 guaranteefraction of photos deleted: 0.64 -> 0.48Improved
Replace greedy photo deletion with optimal deletion selectionVGG-16 collection geolocation scores · Albums, top-1 guaranteefraction of photos deleted: 0.33 -> 0.21Improved
Replace greedy photo deletion with optimal deletion selectionVGG-16 collection geolocation scores · R-16, 12.5% deletion budgetprotected-k: 0.46 -> 0.67Improved
Replace greedy photo deletion with optimal deletion selectionVGG-16 collection geolocation scores · R-32, 50% deletion budgetprotected-k: 7.15 -> 17.49Improved
Aggregate per-image location scores across a collection instead of using a single imageVGG-16 geolocation classifier · R-16top-1 accuracy: 0.20 -> 0.97Improved
Use a higher proxy-score margin for black-box protectionBlack-box top-k guarantee method · R-128success rateMixed

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