Device (In)Dependence of Deep Learning-based Image Age Approximation

TL;DR

This paper investigates whether deep learning models for image age estimation rely on device-specific features by testing models trained on one device across multiple devices, revealing insights into their device dependence.

Contribution

It provides an empirical assessment of the device dependence of CNN-based image age estimation models across multiple devices and camera models.

Findings

Models trained on one device can generalize to other devices to some extent.

Device-specific features are not solely responsible for CNN age predictions.

The study highlights the potential for device-independent age estimation methods.

Abstract

The goal of temporal image forensic is to approximate the age of a digital image relative to images from the same device. Usually, this is based on traces left during the image acquisition pipeline. For example, several methods exist that exploit the presence of in-field sensor defects for this purpose. In addition to these 'classical' methods, there is also an approach in which a Convolutional Neural Network (CNN) is trained to approximate the image age. One advantage of a CNN is that it independently learns the age features used. This would make it possible to exploit other (different) age traces in addition to the known ones (i.e., in-field sensor defects). In a previous work, we have shown that the presence of strong in-field sensor defects is irrelevant for a CNN to predict the age class. Based on this observation, the question arises how device (in)dependent the learned features are. In this work, we empirically asses this by training a network on images from a single device and then apply the trained model to images from different devices. This evaluation is performed on 14 different devices, including 10 devices from the publicly available 'Northumbria Temporal Image Forensics' database. These 10 different devices are based on five different device pairs (i.e., with the identical camera model).