First Steps Toward Camera Model Identification with Convolutional Neural Networks

Abstract

Detecting the camera model used to shoot a picture enables to solve a wide series of forensic problems, from copyright infringement to ownership attribution. For this reason, the forensic community has developed a set of camera model identification algorithms that exploit characteristic traces left on acquired images by the processing pipelines specific of each camera model. In this paper, we investigate a novel approach to solve camera model identification problem. Specifically, we propose a data-driven algorithm based on convolutional neural networks, which learns features characterizing each camera model directly from the acquired pictures. Results on a well-known dataset of 18 camera models show that: (i) the proposed method outperforms up-to-date state-of-the-art algorithms on classification of 64x64 color image patches; (ii) features learned by the proposed network generalize to camera models never used for training.

References in corpus (1)

• Caffe: Convolutional Architecture for Fast Feature Embedding

Cited by in corpus (26)

• Aligned and Non-Aligned Double JPEG Detection Using Convolutional Neural Networks
• Forensic Similarity for Digital Images
• A Counter-Forensic Method for CNN-Based Camera Model Identification
• CNN-based fast source device identification
• DCT-domain Deep Convolutional Neural Networks for Multiple JPEG Compression Classification
• Adversarial Examples in Modern Machine Learning: A Review
• Distinguishing Computer-generated Graphics from Natural Images Based on Sensor Pattern Noise and Deep Learning
• Application of DenseNet in Camera Model Identification and Post-processing Detection
• An In-Depth Study on Open-Set Camera Model Identification
• Identification of Social-Media Platform of Videos through the Use of Shared Features
• Video Source Characterization Using Encoding and Encapsulation Characteristics
• SpliceRadar: A Learned Method For Blind Image Forensics
• First Steps Toward CNN based Source Classification of Document Images Shared Over Messaging App
• A Transferable Anti-Forensic Attack on Forensic CNNs Using A Generative Adversarial Network
• Security Consideration For Deep Learning-Based Image Forensics
• Detecting Colorized Images via Convolutional Neural Networks: Toward High Accuracy and Good Generalization
• Conditional Adversarial Camera Model Anonymization
• Beyond PRNU: Learning Robust Device-Specific Fingerprint for Source Camera Identification
• Fusion of Camera Model and Source Device Specific Forensic Methods for Improved Tamper Detection
• Neural Imaging Pipelines - the Scourge or Hope of Forensics?
• Deep Multi-scale Discriminative Networks for Double JPEG Compression Forensics
• Primary and Secondary Social Media Source Identification
• Using CNNs to Identify the Origin of Finger Vein Image
• The Effect of Class Definitions on the Transferability of Adversarial Attacks Against Forensic CNNs
• VIPPrint: A Large Scale Dataset of Printed and Scanned Images for Synthetic Face Images Detection and Source Linking
• Forensic Scanner Identification Using Machine Learning