PRNU-Bench: A Novel Benchmark and Model for PRNU-Based Camera Identification
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908552291942400 |
|---|---|
| author | Croitoru, Florinel Alin Hondru, Vlad Ionescu, Radu Tudor |
| author_facet | Croitoru, Florinel Alin Hondru, Vlad Ionescu, Radu Tudor |
| contents | We propose a novel benchmark for camera identification via Photo Response Non-Uniformity (PRNU) estimation. The benchmark comprises 13K photos taken with 120+ cameras, where the training and test photos are taken in different scenarios, enabling ``in-the-wild'' evaluation. In addition, we propose a novel PRNU-based camera identification model that employs a hybrid architecture, comprising a denoising autoencoder to estimate the PRNU signal and a convolutional network that can perform 1:N verification of camera devices. Instead of using a conventional approach based on contrastive learning, our method takes the Hadamard product between reference and query PRNU signals as input. This novel design leads to significantly better results compared with state-of-the-art models based on denoising autoencoders and contrastive learning. We release our dataset and code at: https://github.com/CroitoruAlin/PRNU-Bench. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17581 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PRNU-Bench: A Novel Benchmark and Model for PRNU-Based Camera Identification Croitoru, Florinel Alin Hondru, Vlad Ionescu, Radu Tudor Computer Vision and Pattern Recognition Cryptography and Security Machine Learning We propose a novel benchmark for camera identification via Photo Response Non-Uniformity (PRNU) estimation. The benchmark comprises 13K photos taken with 120+ cameras, where the training and test photos are taken in different scenarios, enabling ``in-the-wild'' evaluation. In addition, we propose a novel PRNU-based camera identification model that employs a hybrid architecture, comprising a denoising autoencoder to estimate the PRNU signal and a convolutional network that can perform 1:N verification of camera devices. Instead of using a conventional approach based on contrastive learning, our method takes the Hadamard product between reference and query PRNU signals as input. This novel design leads to significantly better results compared with state-of-the-art models based on denoising autoencoders and contrastive learning. We release our dataset and code at: https://github.com/CroitoruAlin/PRNU-Bench. |
| title | PRNU-Bench: A Novel Benchmark and Model for PRNU-Based Camera Identification |
| topic | Computer Vision and Pattern Recognition Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2509.17581 |