Aligned and Non-Aligned Double JPEG Detection Using Convolutional Neural Networks

Abstract

Due to the wide diffusion of JPEG coding standard, the image forensic community has devoted significant attention to the development of double JPEG (DJPEG) compression detectors through the years. The ability of detecting whether an image has been compressed twice provides paramount information toward image authenticity assessment. Given the trend recently gained by convolutional neural networks (CNN) in many computer vision tasks, in this paper we propose to use CNNs for aligned and non-aligned double JPEG compression detection. In particular, we explore the capability of CNNs to capture DJPEG artifacts directly from images. Results show that the proposed CNN-based detectors achieve good performance even with small size images (i.e., 64x64), outperforming state-of-the-art solutions, especially in the non-aligned case. Besides, good results are also achieved in the commonly-recognized challenging case in which the first quality factor is larger than the second one.

Submitted to Journal of Visual Communication and Image Representation (first submission: March 20, 2017; second submission: August 2, 2017)

References in corpus (1)

• First Steps Toward Camera Model Identification with Convolutional Neural Networks

Cited by in corpus (24)

• MesoNet: a Compact Facial Video Forgery Detection Network
• Media Forensics and DeepFakes: an overview
• FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signals
• Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization
• Forensic Similarity for Digital Images
• Exposing Fake Images with Forensic Similarity Graphs
• DCT-domain Deep Convolutional Neural Networks for Multiple JPEG Compression Classification
• Deep Convolutional Neural Network for Identifying Seam-Carving Forgery
• Detecting Photoshopped Faces by Scripting Photoshop
• Detecting Deepfake-Forged Contents with Separable Convolutional Neural Network and Image Segmentation
• Zooming into Face Forensics: A Pixel-level Analysis
• Security Consideration For Deep Learning-Based Image Forensics
• Image Splicing Detection, Localization and Attribution via JPEG Primary Quantization Matrix Estimation and Clustering
• Detecting Colorized Images via Convolutional Neural Networks: Toward High Accuracy and Good Generalization
• In-Depth DCT Coefficient Distribution Analysis for First Quantization Estimation
• Primary quantization matrix estimation of double compressed JPEG images via CNN
• Statistical Analysis of Signal-Dependent Noise: Application in Blind Localization of Image Splicing Forgery
• Deep Multi-scale Discriminative Networks for Double JPEG Compression Forensics
• Camera Model Identification Using Convolutional Neural Networks
• Fighting Fake News: Image Splice Detection via Learned Self-Consistency
• Q-matrix Unaware Double JPEG Detection using DCT-Domain Deep BiLSTM Network
• Recompression Based JPEG Tamper Detection and Localization Using Deep Neural Network Eliminating Compression Factor Dependency
• Large-Scale and Fine-Grained Evaluation of Popular JPEG Forgery Localization Schemes
• Boosting CNN-based primary quantization matrix estimation of double JPEG images via a classification-like architecture