In order to improve the robustness and capability of resisting image steganalysis, a novel coverless image steganography algorithm based on Discrete Cosine Transform and Latent Dirichlet Allocation topic classification is proposed. Firstly, LDA topic model is utilized for classifying the image database. Secondly, the images belong to one topic are selected, and 8×8 block DCT transform is performed to these images. Then robust feature sequence is generated through the relation between Direct Current coefficients in the adjacent blocks. Finally, an inverted index which contains the feature sequence, $dc$, location coordinates and image path is created. For the purpose of achieving image steganography, the secret information is converted into a binary sequence and partitioned into segments, and the image whose feature sequence equals to the secret information segments is chosen as the cover image according to the index. After that, all cover images are sent to the receiver. In the whole process, no modification is done to the original images. Experimental results and analysis show that the proposed algorithm can resist the detection of existing steganalysis algorithms, and has better robustness against common image processing and better ability to resist steganalysis compared with the existing coverless image steganography algorithms. Meanwhile, it is resistant to geometric attacks to some extent. It has great potential application in secure communication of big data environment.
Face morphing attack is proved to be a serious threat to the existing face recognition systems. Although a few face morphing detection methods have been put forward, the face morphing accomplice’s facial restoration remains a challenging problem. In this paper, a face de-morphing generative adversarial network (FD-GAN) is proposed to restore the accomplice’s facial image. It utilizes a symmetric dual network architecture and two levels of restoration losses to separate the identity feature of the morphing accomplice. By exploiting the captured facial image (containing the criminal’s identity) from the face recognition system and the morphed image stored in the e-passport system (containing both criminal and accomplice’s identities), the FD-GAN can effectively restore the accomplice’s facial image. Experimental results and analysis demonstrate the effectiveness of the proposed scheme. It has great potential to be applied for tracing the identity of face morphing attack’s accomplice in criminal investigation and judicial forensics.
22 March 2022 in IEEE Transactions on Circuits and Systems for Video Technology
Aiming at resolving the problem of the irreversibility in some common neural networks for secret data extraction, a novel image steganography framework is proposed based on the generator of GAN (Generative Adversarial Networks) and gradient descent approximation. During data embedding, the secret data is first mapped into a stego noise vector by a specific mapping rule, and it is input into the generator of a GAN to produce a stego image. The data extraction is accomplished by iteratively updating the noise vector using the gradient descent with the generator. When the error is declined within the allowable error, the output image of the generator is approximate to the stego image, and the updated noise vector will also approach to the stego noise vector. Finally, the secret data is extracted from the updated noise vector. Experiments and analysis with WGAN-GP (Wasserstein GAN-Gradient Penalty) show that it can achieve good performance in extraction accuracy, capacity and robustness. Furthermore, the discussions also illustrate its good generalization with different GAN models and image datasets.
26 June 2019 in IEEE Transactions on Circuits and Systems for Video Technology
Designing selective encryption (SE) schemes for H.265/HEVC has been attracted much attention with the advent of H.265/HEVC codec in the past two decades. However, most SE algorithms for H.265/HEVC encrypt the syntax elements in bypass mode to keep the bit rate. Moreover, the edge region of the video data is not sufficiently protected. To produce large visual distor-tion and edge loss, a tunable SE scheme for H.265/HEVC based on chroma intra prediction mode (IPM) and coefficient scrambling is proposed. Firstly, a pseudo-random number sequence is generated by AES-CTR. Then, the prediction, residual and reconstruction information in H.265/HEVC encoding process are encrypted by a pseudo-random sequence. It encrypts the syntax elements of con-text-based adaptive binary arithmetic coding (CABAC) in bypass mode. Some syntax elements including chroma IPM in regular mode are encrypted as well. To further protect the edge infor-mation, a coefficient scrambling is adopted. The edge information of each frame is extracted and the Transform Units (TUs) are clas-sified according to it. Then, coefficients of the TUs containing edge are scrambled. Finally, a sign used for marking the type of each TU is embedded into a coefficient. Experimental results and anal-ysis show that the proposed scheme has better visual distortion and subjective evaluation results compared with some existing H.265/HEVC SE algorithms. Meanwhile, users can flexibly use the proposed SE scheme according to encryption performance and bit rate requirements, which is attractive in the scenario of protecting video in cloud servers.
25 October 2017 in Journal of Real-Time Image Processing