Jing Dong

Deep learning for steganalysis via convolutional neural networks

Current work on steganalysis for digital images is focused on the construction of complex handcrafted features. This paper proposes a new paradigm for steganalysis to learn features automatically via deep learning models. We novelly propose a customized Convolutional Neural Network for steganalysis. The proposed model can capture the complex dependencies that are useful for steganalysis. Compared with existing schemes, this model can automatically learn feature representations with several convolutional layers. The feature extraction and classification steps are unified under a single architecture, which means the guidance of classification can be used during the feature extraction step. We demonstrate the effectiveness of the proposed model on three state-of-theart spatial domain steganographic algorithms - HUGO, WOW, and S-UNIWARD. Compared to the Spatial Rich Model (SRM), our model achieves comparable performance on BOSSbase and the realistic and large ImageNet database.

Effective image splicing detection based on image chroma

A color image splicing detection method based on gray level co-occurrence matrix (GLCM) of thresholded edge image of image chroma is proposed in this paper. Edge images are generated by subtracting horizontal, vertical, main and minor diagonal pixel values from current pixel values respectively and then thresholded with a predefined threshold T. The GLCMs of edge images along the four directions serve as features for image splicing detection. Boosting feature selection is applied to select optimal features and Support Vector Machine (SVM) is utilized as classifier in our approach. The effectiveness of the proposed method has been demonstrated by our experimental results.

Run-Length and Edge Statistics Based Approach for Image Splicing Detection

In this paper, a simple but efficient approach for blind image splicing detection is proposed. Image splicing is a common and fundamental operation used for image forgery. The detection of image splicing is a preliminary but desirable study for image forensics. Passive detection approaches of image splicing are usually regarded as pattern recognition problems based on features which are sensitive to splicing. In the proposed approach, we analyze the discontinuity of image pixel correlation and coherency caused by splicing in terms of image run-length representation and sharp image characteristics. The statistical features extracted from image run-length representation and image edge statistics are used for splicing detection. The support vector machine (SVM) is used as the classifier. Our experimental results demonstrate that the two proposed features outperform existing ones both in detection accuracy and computational complexity.

Image tampering detection based on stationary distribution of Markov chain

In this paper, we propose a passive image tampering detection method based on modeling edge information. We model the edge image of image chroma component as a finite-state Markov chain and extract low dimensional feature vector from its stationary distribution for tampering detection. The support vector machine (SVM) is utilized as classifier to evaluate the effectiveness of the proposed algorithm. The experimental results in a large scale of evaluation database illustrates that our proposed method is promising.

Effects of watermarking on iris recognition performance

Protection of biometric data and templates is a crucial issue for the security of biometric systems, and biometric watermarking is introduced for this purpose. However, watermarking introduces extra information into the biometric data (biometric images or biometric feature templates) which leads to certain distortion. In addition, watermarked images are always subject to the risk of being attacked. Hence, whether and how biometric recognition performance will be affected by biometric watermarking deserves investigation. In this paper, we make a first attempt in such investigations by studying two application scenarios in the context of iris recognition, namely protection of iris templates by hiding them in cover images as watermarks (iris watermarks), and protection of iris images by watermarking them. Experimental results suggest that watermark embedding in iris images does not introduce detectable decreases on iris recognition performance whereas recognition performance drops significantly if iris watermarks suffer from severe attacks.

Fragile image watermarking with pixel-wise recovery based on overlapping embedding strategy

Overlapping-block embedding strategy is introduced in the proposed scheme.Two possible embedding modes are utilized for the blocks based on the locations.Authentication-bits are generated according to the complexity of each block.Block-wise tampering detection and pixel-wise content recovery are collaborated.Better tampering recovery performance can be achieved than some of reported schemes. In this paper, we propose a new fragile watermarking scheme with high-quality recovery capability based on overlapping embedding strategy. The block-wise mechanism for tampering localization and the pixel-wise mechanism for content recovery are collaborated in the proposed scheme. With the assist of interleaving operation, reference bits are derived from mean value of each overlapping block, and then are dispersedly embedded into 1 LSB or 2 LSB layers of the image, corresponding to horizontal-vertical mode and diagonal mode, respectively. Authentication bits are hidden into adaptive LSB layers of the central pixel for each block according to block complexity. On the receiver side, after locating tampered blocks and reconstructing mean-value bits, according to the types of tampered pixels in each overlapping block, three pixel-wise manners are exploited for tampering recovery based on different neighboring blocks. Even if the tampered area is extensive, the proposed scheme can achieve better quality of recovered image compared with some of state-of-the-art schemes.

A Survey of Passive Image Tampering Detection

Digital images can be easily tampered with image editing tools. The detection of tampering operations is of great importance. Passive digital image tampering detection aims at verifying the authenticity of digital images without any a prior knowledge on the original images. There are various methods proposed in this filed in recent years. In this paper, we present an overview of these methods in three levels, that is low level, middle level, and high level in semantic sense. The main ideas of the proposed approaches at each level are described in detail, and some comments are given.

Learning and transferring representations for image steganalysis using convolutional neural network

The major challenge of machine learning based image steganalysis lies in obtaining powerful feature representations. Recently, Qian et al. have shown that Convolutional Neural Network (CNN) is effective for learning features automatically for steganalysis. In this paper, we follow up this new paradigm in steganalysis, and propose a framework based on transfer learning to help the training of CNN for steganalysis, hence to achieve a better performance. We show that feature representations learned with a pre-trained CNN for detecting a steganographic algorithm with a high payload can be efficiently transferred to improve the learning of features for detecting the same steganographic algorithm with a low pay-load. By detecting representative WOW and S-UNIWARD steganographic algorithms, we demonstrate that the proposed scheme is effective in improving the feature learning in CNN models for steganalysis.

CASIA Image Tampering Detection Evaluation Database

Image forensics has now raised the anxiety of justice as increasing cases of abusing tampered images in newspapers and court for evidence are reported recently. With the goal of verifying image content authenticity, passive-blind image tampering detection is called for. More realistic open benchmark databases are also needed to assist the techniques. Recently, we collect a natural color image database with realistic tampering operations. The database is made publicly available for researchers to compare and evaluate their proposed tampering detection techniques. We call this database CASI-A Image Tampering Detection Evaluation Database. We describe the purpose, the design criterion, the organization and self-evaluation of this database in this paper.

Exploring DCT Coefficient Quantization Effects for Local Tampering Detection

In this paper, we focus on local image tampering detection. For a JPEG image, the probability distributions of its DCT coefficients will be disturbed by tampering operation. The tampered region and the unchanged region have different distributions, which is an important clue for locating tampering. Based on the assumption of Laplacian distribution of unquantized ac DCT coefficients, these two distributions as well as the size of tampered region can be estimated so that the probability of each DCT block being tampered is obtained. More accurate localization results could be got when we consider the prior knowledge of common tampered regions. We also design three kinds of features that can distinguish truly tampered regions from the false ones to reduce false alarm. For a tampered image which is saved in lossless compressed format, we also propose the specialized approach, which employs the quantization noise of high-frequency DCT coefficient, to improve the tampering localization performance. Extensive experiments on large scale databases prove the effectiveness of our proposed method and demonstrate that our method is suitable for locating tampered regions with different scales.