# Combining PRNU and noiseprint for robust and efficient device source identification

arXiv: https://arxiv.org/abs/2001.06440 · HTML: https://mlsanity.com/paper/2001.06440/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jan 2020.

## Built on by (most cited first, 6 of 6)

- [Revisiting Model's Uncertainty and Confidences for Adversarial Example Detection](https://mlsanity.com/paper/2103.05354/) (2021)
- [Fusion-based Few-Shot Morphing Attack Detection and Fingerprinting](https://mlsanity.com/paper/2210.15510/) (2022)
- [Identification of Social-Media Platform of Videos through the Use of Shared Features](https://mlsanity.com/paper/2109.03598/) (2021)
- [Datasets, Clues and State-of-the-Arts for Multimedia Forensics: An Extensive Review](https://mlsanity.com/paper/2401.06999/) (2024)
- [PRNU-Bench: A Novel Benchmark and Model for PRNU-Based Camera Identification](https://mlsanity.com/paper/2509.17581/) (2025)
- [Zero-Shot Color Image Manipulation Localization via Noise Residual Artifact Pattern Analysis](https://mlsanity.com/paper/2608.20558/) (2026)

## Abstract (arXiv)

PRNU-based image processing is a key asset in digital multimedia forensics. It allows for reliable device identification and effective detection and localization of image forgeries, in very general conditions. However, performance impairs significantly in challenging conditions involving low quality and quantity of data. These include working on compressed and cropped images, or estimating the camera PRNU pattern based on only a few images. To boost the performance of PRNU-based analyses in such conditions we propose to leverage the image noiseprint, a recently proposed camera-model fingerprint that has proved effective for several forensic tasks. Numerical experiments on datasets widely used for source identification prove that the proposed method ensures a significant performance improvement in a wide range of challenging situations.