# Forensic Analysis for Source Camera Identification from EXIF Metadata

## TL;DR

This paper introduces a new forensic method using EXIF metadata to identify the source camera of smartphone images, improving accuracy and understanding of modern camera behaviors.

## Contribution

A novel forensic analysis framework using EXIF metadata with type-aware word embeddings to interpret and address anomalous behaviors in modern devices.

## Key findings

- The proposed EXIF-based method achieves state-of-the-art performance in source camera identification.
- The framework provides interpretable insights into anomalous device behaviors observed in modern smartphones.
- Type-aware word embeddings effectively preserve contextual information across EXIF tags for accurate analysis.

## Abstract

Source camera identification on smartphones constitutes a fundamental task in multimedia forensics, providing essential support for applications such as image copyright protection, illegal content tracking, and digital evidence verification. Numerous techniques have been developed for this task over the past decades. Among existing approaches, Photo-Response Non-Uniformity (PRNU) has been widely recognized as a reliable device-specific fingerprint and has demonstrated remarkable performance in real-world applications. Nevertheless, the rapid advancement of computational photography technologies has introduced significant challenges: modern devices often exhibit anomalous behaviors under PRNU-based analysis. For instance, images captured by different devices may exhibit unexpected correlations, while images captured by the same device can vary substantially in their PRNU patterns. Current approaches are incapable of automatically exploring the underlying causes of these anomalous behaviors. To address this limitation, we propose a simple yet effective forensic analysis framework leveraging Exchangeable Image File Format (EXIF) metadata. Specifically, we represent EXIF metadata as type-aware word embeddings to preserve contextual information across tags. This design enables visual interpretation of the model’s decision-making process and provides complementary insights for identifying the anomalous behaviors observed in modern devices. Extensive experiments conducted on three public benchmark datasets demonstrate that the proposed method not only achieves state-of-the-art performance for source camera identification but also provides valuable insights into anomalous device behaviors.