Deepfake technologies leverage deep learning to generate highly realistic videos involving face swapping and expression transfer, often exceeding the threshold of human visual perception. This poses serious challenges to social governance and digital security, highlighting the urgent need for reliable forgery detection methods. Training detection models without using real forgeries is considered a promising strategy to improve generalization. These approaches simulate diverse forgery traces to generate synthetic training data. However, most existing methods rely on 2 D image manipulation and fail to capture 3D forgery characteristics such as geometric distortion, expression mismatch, and texture anomalies-leading to poor performance on reconstruction-based forgeries. To address this problem, we propose a Reconstruction-Blended Image (RBI) generation method based on 3D Morphable Models (3DMM). By perturbing facial shape and expression parameters, this approach produces training samples that better reflect 3D reconstruction artifacts. When combined with traditional Self-Blended Images (SBI), the hybrid training strategy enhances the model's ability to detect a wider range of forgeries. Experiments show that this method improves AUC by$\mathbf{1 0. 7 9} \boldsymbol{\%}$on challenging cases like Face2Face forgeries. In summary, our 3D face reconstruction-based generation strategy significantly enhances the generalization and robustness of forgery detection models, offering a practical solution to emerging deepfake threats.

Sophisticated and realistic facial manipulation videos created by deepfake technology have become ubiquitous, leading to profound trust crises and security risks in contemporary society. However, various researchers concentrate on enhancing the precision and generalization of deepfake detection models, with little attention to forgery localization. Detecting deepfakes and identifying fake regions is a challenging task. We propose an end-to-end model for performing deepfake detection and forgery localization based on the Laplacian pyramid. The model is designed by an encoder–decoder architecture. Specifically, the encoder generates multi-scale features. The decoder gradually integrates multi-scale features and Laplacian residuals to reconstruct the prediction masks coarse-to-finely. Otherwise, we adopt a spatial pyramid pool approach to deal with high-level semantic features and integrate local and global information. Comprehensive experiments demonstrate that the proposed model performs satisfactorily in deepfake detection and localization.

With the increasing development of deepfake in facial editing and the easy accessibility of image and video content on the internet, the security risks of spreading false personal information through social media platforms are becoming increasingly serious. The harm caused by deepfake includes spreading false information, pornography, financial fraud, privacy breaches, and security system damage. To address these security issues, it is necessary to strengthen the detection and defense of deepfake. Current research mainly focuses on the detection of deepfake images and videos. In recent years, some work has proposed using the method of generating adversarial samples to deal with the malicious operations of GAN networks in deepfake. And it has proposed different single perturbation fusion methods to generate universal adversarial watermarks that can defend against modifications by multiple models. However, all of these works generate single-step watermarks using gradient-based methods, which cannot accurately control the required perturbation strength, resulting in large errors and more irrelevant information compared to the original image after superimposing the watermark. To solve this problem, we propose an optimized adversarial face deepfake watermark and measure the protection success rate and defense performance of this method on single and multiple models. From the extensive experimental results, we find that the perturbation generated by the Optimization-based method can successfully generate smaller perturbations while ensuring a high protection success rate, making the adversarial samples closer to the original samples. It can also be applied to different types of models and loss functions, accurately generating perturbation strength, and has a wider range of applicability.

Summary Symmetric searchable encryption (SSE) enables users to search the ciphertext stored on the untrusted cloud without revealing the search keywords, effectively protecting users' privacy. However, most of the existing SSE schemes reveal the search or access pattern during the keyword query, which can be used by the adversary to infer the sensitive information in ciphertext, thus posing a great threat to users' privacy. To address this, we propose an SSE scheme supporting search pattern and access pattern protection in multi‐cloud, called SAPM‐SSE. In our scheme, an index shuffle protocol is proposed to change the content and location of the index after each query, which helps to achieve the protection of search and access pattern. Furthermore, with the purpose of improving the efficiency of shuffling, we construct a shuffling algorithm based on index cache, the number of index entries for shuffling reduced from γ to γ/n (n≥1). Besides, our scheme supports the dynamic update of documents and achieves the forward security in update. Finally, security analysis and experimental results show that our scheme can achieve the protection of search pattern and access pattern with high efficiency.

Abstract With the popularity of cloud computing, cloud storage technology has also been widely used. Among them, data integrity verification is a hot research topic. At present, the realization of public auditing has become the development trend of integrity verification. Most existing public auditing schemes rarely consider some indispensable functions at the same time. Thus, in this article, we propose a comprehensive public auditing scheme (PDBPA) that can simultaneously support data privacy protection, data dynamics, and multi‐user batch auditing. To guarantee privacy protection during the audit process, our PDBPA design a new method of constructing audit proof, which combines random masking techniques and bilinear properties of bilinear pairing. Not only can it ensure that TPA performs audits correctly, but it can also prevent it from exploring the user's sensitive data. In addition, by utilizing the modified dynamic hash table, which is a novel and small two‐dimensional data structure, data dynamics can be effectively achieved. Furthermore, we provide a detailed process for the third‐party auditors to perform batch audits for multiple users. Moreover, we give the detailed and rigorous security analysis in defending against forgery attack, replace attack, and replay attack. Performance evaluations demonstrate that our PDBPA scheme is effective and feasible.