Apple’s Synthetic Defocus Noise Pattern: Characterization and Forensic Applications
Open Access
- 12 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 1096-1111
Abstract
iPhone portrait-mode images contain a distinctive pattern in out-of-focus regions simulating the bokeh effect, which we term Apple’s Synthetic Defocus Noise Pattern (SDNP). If overlooked, this pattern can interfere with blind forensic analyses, especially PRNU-based camera source verification, as noted in earlier works. Since Apple’s SDNP remains underexplored, we provide a detailed characterization, proposing a method for its precise estimation, modeling its dependence on scene brightness, ISO settings, and other factors. Leveraging this characterization, we explore forensic applications of the SDNP, including traceability of portrait-mode images across iPhone models and iOS versions in open-set scenarios, assessing its robustness under post-processing. Furthermore, we show that masking SDNP-affected regions in PRNU-based camera source verification significantly reduces false positives, overcoming a critical limitation in camera attribution, and improving state-of-the-art techniques.Keywords
All Related Versions
Funding Information
- EU (Next Generation) through the “Plan de Recuperación, Transformación y Resiliencia” Project FELDSPAR: “Federated Learning with Model Ownership Protection and Privacy Armoring” (MCIN/AEI/10.13039/501100011033)
- Xunta de Galicia and the European Regional Development Fund (ED431C 2021/47)
- Xunta de Galicia and the European Regional Development Fund (ED431C 2025/41)
- open access funding provided by Universidade de Vigo/CISUG
This publication has 18 references indexed in Scilit:
- Source camera attribution via PRNU emphasis: Towards a generalized multiplicative modelSignal Processing: Image Communication, 2023
- Investigating Inconsistencies in PRNU-Based Camera Identification2022
- Computational Imaging2022
- Checking PRNU Usability on Modern Devices2021
- Facing Image Source Attribution on iPhone X2021
- A Leak in PRNU Based Source Identification—Questioning Fingerprint UniquenessIEEE Access, 2021
- A Style-Based Generator Architecture for Generative Adversarial Networks2019
- Fast sequential forensic detection of camera fingerprint2016
- Determining Image Origin and Integrity Using Sensor NoiseIEEE Transactions on Information Forensics and Security, 2008
- Spatially adaptive statistical modeling of wavelet image coefficients and its application to denoising1999