Research map / Federated learning and privacy / Privacy attacks and secure learning
Privacy-CNH: A Framework to Detect Photo Privacy with Convolutional Neural Network using Hierarchical Features
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| add ImageNet transfer learning (pretrain then fine-tune) (ablation) | PCNH · Zerr et al. 2012 dataset | Accuracy: 0.83 -> 0.95 | Helped |
| add ImageNet transfer learning (ablation) | PCNH · Our privacy dataset | Accuracy: 0.80 -> 0.90 | Helped |
| add ImageNet transfer learning (ablation) | PCNN · Zerr et al. 2012 dataset | Accuracy: 0.74 -> 0.89 | Helped |
| add ImageNet transfer learning (ablation) | PONN · Zerr et al. 2012 dataset | Accuracy: 0.67 -> 0.71 | Helped |
| add object features (PONN) to convolutional features (PCNN) (ablation) | PCNN with transfer learning · Zerr et al. 2012 dataset | Accuracy: 0.89 -> 0.95 | Helped |
| add object features (PONN) to convolutional features (PCNN) (ablation) | PCNN with transfer learning · Our privacy dataset | Accuracy: 0.84 -> 0.90 | Helped |
| add object features (PONN) to convolutional features (PCNN), no transfer (ablation) | PCNN · Zerr et al. 2012 dataset | Accuracy: 0.74 -> 0.83 | Helped |
| add convolutional features to object features (ablation) | PONN · Our privacy dataset | Accuracy: 0.65 -> 0.80 | Helped |
| replace BOVW+SVM with CNN-based PCNH with transfer | SVM + BOVW · Zerr et al. 2012 dataset | Accuracy: 0.65 -> 0.95 | Helped |
Closest papers by meaning
- Balancing Privacy and Performance: A Many-in-One Approach for Image Anonymization (AAAI 2025 · similarity 0.84)
- Validating Privacy-Preserving Face Recognition under a Minimum Assumption (CVPR 2024 · similarity 0.84)
- MultiPriv: Benchmarking Individual-Level Privacy Reasoning in Vision-Language Models (ICML 2026 · similarity 0.83)
- Private Attribute Inference from Images with Vision-Language Models (NeurIPS 2024 · similarity 0.82)
- PerceptAnon: Exploring the Human Perception of Image Anonymization Beyond Pseudonymization for GDPR (ICML 2024 · similarity 0.82)
- ViP: A Differentially Private Foundation Model for Computer Vision (ICML 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.