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
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
- Differentially Private 2D Human Pose Estimation (CVPR 2026 · similarity 0.90)
- Learning Privacy-Preserving Optics for Human Pose Estimation (ICCV 2021 · similarity 0.86)
- Validating Privacy-Preserving Face Recognition under a Minimum Assumption (CVPR 2024 · similarity 0.84)
- PerceptAnon: Exploring the Human Perception of Image Anonymization Beyond Pseudonymization for GDPR (ICML 2024 · similarity 0.83)
- EgoPrivacy: What Your First-Person Camera Says About You? (ICML 2025 · similarity 0.83)
- LPSNet: End-to-End Human Pose and Shape Estimation with Lensless Imaging (CVPR 2024 · similarity 0.82)
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.
