Diagonal Artifacts in Samsung Images: PRNU Challenges and Solutions

2025-10-10

AI Summary

This study identifies a prevalent diagonal artifact in images from select Samsung Galaxy S/A-series smartphones and its adverse impact on PRNU-based camera source identification, causing spurious fingerprint collisions. Through systematic PRNU fingerprint analysis, artifact detection, RAW–JPEG comparative evaluation, and multi-mode image processing pipeline modeling, the authors demonstrate that the artifact originates from a shared ISP pipeline, inducing abnormally high inter-device PRNU similarity. Methodologically, the work introduces the “artifact-assisted forensics” paradigm: (i) RAW images captured in PRO mode bypass the artifact, enabling reliable source attribution; and (ii) the artifact itself serves as a discriminative signal for detecting HDR misclassification and localizing bokeh regions in portrait mode. The findings establish novel forensic criteria and practical countermeasures for mobile device source identification—particularly when original (RAW) images are unavailable.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Intelligent Robots: Localization, Mapping, and Navigation
• Machine Learning: Privacy

Application Category

• Security and Privacy: Data transparency and provenance
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

We investigate diagonal artifacts present in images captured by several Samsung smartphones and their impact on PRNU-based camera source verification. We first show that certain Galaxy S series models share a common pattern causing fingerprint collisions, with a similar issue also found in some Galaxy A models. Next, we demonstrate that reliable PRNU verification remains feasible for devices supporting PRO mode with raw capture, since raw images bypass the processing pipeline that introduces artifacts. This option, however, is not available for the mid-range A series models or in forensic cases without access to raw images. Finally, we outline potential forensic applications of the diagonal artifacts, such as reducing misdetections in HDR images and localizing regions affected by synthetic bokeh in portrait-mode images.

Problem

• Investigating diagonal artifacts in Samsung smartphone images affecting PRNU verification
• Demonstrating raw images bypass artifact-causing processing for reliable verification
• Exploring forensic applications of artifacts for HDR and portrait-mode analysis

Innovation

• Using raw images to bypass artifact-inducing processing pipeline
• Identifying diagonal artifacts to reduce HDR misdetections
• Leveraging artifacts for synthetic bokeh localization in portraits