A Counter-Forensic Method for CNN-Based Camera Model Identification

TL;DR

This paper presents a method to subtly alter images using adversarial attacks, fooling CNN-based camera model detectors without needing access to the model, exposing vulnerabilities in current forensic techniques.

Contribution

It introduces a counter-forensic approach that employs FGSM and JSMA attacks to deceive CNN-based camera model identification systems without direct model access.

Findings

Adversarial examples can successfully spoof camera model detection.

Deep CNNs remain vulnerable to crafted adversarial images.

The method works across various CNN architectures.

Abstract

An increasing number of digital images are being shared and accessed through websites, media, and social applications. Many of these images have been modified and are not authentic. Recent advances in the use of deep convolutional neural networks (CNNs) have facilitated the task of analyzing the veracity and authenticity of largely distributed image datasets. We examine in this paper the problem of identifying the camera model or type that was used to take an image and that can be spoofed. Due to the linear nature of CNNs and the high-dimensionality of images, neural networks are vulnerable to attacks with adversarial examples. These examples are imperceptibly different from correctly classified images but are misclassified with high confidence by CNNs. In this paper, we describe a counter-forensic method capable of subtly altering images to change their estimated camera model when they are analyzed by any CNN-based camera model detector. Our method can use both the Fast Gradient Sign Method (FGSM) or the Jacobian-based Saliency Map Attack (JSMA) to craft these adversarial images and does not require direct access to the CNN. Our results show that even advanced deep learning architectures trained to analyze images and obtain camera model information are still vulnerable to our proposed method.