Constrained Convolutional Neural Networks: A New Approach Towards General Purpose Image Manipulation Detection

By Belhassen Bayar, Matthew Christopher Stamm. IEEE Transactions on Information Forensics and Security, 2018

534 citations recorded by the source corpus.

Identifying the authenticity and processing history of an image is an important task in multimedia forensics. By analyzing traces left by different image manipulations, researchers have been able to develop several algorithms capable of detecting targeted editing operations. While this approach has led to the development of several successful forensic algorithms, an important problem remains: creating forensic detectors for different image manipulations is a difficult and time consuming process. Furthermore, forensic analysts need general purpose forensic algorithms capable of detecting multiple different image manipulations. In this paper, we address both of these problems by proposing a new general purpose forensic approach using convolutional neural networks (CNNs). While CNNs are capable of learning classification features directly from data, in their existing form they tend to learn features representative of an image’s content. To overcome this issue, we have developed a new type of CNN layer, called a constrained convolutional layer, that is able to jointly suppress an image’s content and adaptively learn manipulation detection features. Through a series of experiments, we show that our proposed constrained CNN is able to learn manipulation detection features directly from data. Our experimental results demonstrate that our CNN can detect multiple different editing operations with up to 99.97% accuracy and outperform the existing state-of-the-art general purpose manipulation detector. Furthermore, our constrained CNN can still accurately detect image manipulations in realistic scenarios where there is a source camera model mismatch between the training and testing data.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/70c8253c6954e3f02760dea1a6f701c0e18bde18

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

SPAN: Spatial Pyramid Attention Network forImage Manipulation Localization (2020, methodology): “Manipulation Detection and Localization: Most of existing methods detect and localization a specific type of manipulation only, such as copy-move[7,27,33], removal[44], enhancement[5,6], and splicing[8,16,18,29].”
Depth-Wise Separable Convolutions and Multi-Level Pooling for an Efficient Spatial CNN-Based Steganalysis (2020, methodology): “In [52], [53], they randomly initialize the convolution kernel of the preprocessing layer and constrain the weights of the filters to have a null sum and to have a −1 value in the center at back-propagation.”
ManTra-Net: Manipulation Tracing Network for Detection and Localization of Image Forgeries With Anomalous Features (2019, methodology): “We compare the known optimal settings for SRMConv2D from [55] and BayarConv2D from [10] with the classic Conv2D layers, and a combined version of all three, which is simply the feature concatenation as shown in Fig.”
MVSS-Net: Multi-View Multi-Scale Supervised Networks for Image Manipulation Detection (2021, methodology): “2 shows, letting the given image x go through a BayarConv layer with kernel size of 5 5 3, we obtain its full-sized noise view as BayarConvðxÞ.”