AI Paper Atlas

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

Don’t call it privacy-preserving or human-centric pose estimation if you don’t measure privacy

Michele Baldassini, Francesco Pistolesi, Beatrice Lazzerini

NeurIPS 2025 · Federated learning and privacy › Privacy attacks and secure learning · approach: Visual privacy and face de-identification

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Position paper arguing that human pose estimation systems cannot be called privacy-preserving or human-centric unless privacy is explicitly measured and evaluated.

Problem

Human pose estimation (HPE) systems are evaluated almost exclusively with accuracy metrics, while privacy is neither defined in measurable terms nor linked to regulatory requirements, and common deployment architectures may leak sensitive information.

Approach

Argues that privacy claims for HPE should be backed by measurable privacy evaluation and tied to regulatory requirements, rather than being asserted based on accuracy-only assessment.

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