The protection of user private data has long been the focus of AI security. We know that training machine learning models rely on large amounts of user data. However, user data often exists in the form of isolated islands that can not be integrated under many secure and legal constraints. The large-scale application of image steganalysis algorithms in real life is still not satisfactory due to the following challenges. First, it is difficult to aggregate all of the scattered steganographic images to train a robust classifier. Second, even if the images are encrypted, participants do not want irrelevant people to peek into the hidden information, resulting in the disclosure of private data. Finally, it is often impossible for different participants to train their tailored models. In this paper, we introduce a novel framework, referred to as FedSteg, to train a secure, personalized distributed model through federated transfer learning to fulfill secure image steganalysis. Extensive experiments on detecting several state-of-the-art steganographic methods i.e., WOW, S-UNIWARD, and HILL, validate that FedSteg achieves certain improvements compared to traditional non-federated steganalysis approaches. In addition, FedSteg is highly extensible and can be easily employed to various large-scale secure steganographic recognition tasks.

In recent years, to address the issue of networked data sparsity in node classification tasks, cross-network node classification (CNNC) leverages the richer information from a source network to enhance the performance of node classification in the target network, which typically has sparser information. However, in real-world applications, labeled nodes may be collected from multiple sources with multiple modalities (e.g., text, vision, and video). Naive application of single-source and single-modal CNNC methods may result in sub-optimal solutions. To this end, in this article, we propose a model called Multi-source and Multi-modal Cross-network Deep Network Embedding (M ² CDNE) for cross-network node classification. In M ² CDNE, we propose a deep multi-modal network embedding approach that combines the extracted deep multi-modal features to make the node vector representations network invariant. In addition, we apply dynamic adversarial adaptation to assess the significance of marginal and conditional probability distributions between each source and target network to make node vector representations label discriminative. Furthermore, we devise to classify nodes in the target network through the related source classifier and aggregate different predictions utilizing respective network weights, corresponding to the discrepancy between each source and target network. Extensive experiments performed on real-world datasets demonstrate that the proposed M ² CDNE significantly outperforms the state-of-the-art approaches.

Image posting and sharing on the social media clouds is a common activity of end users. During the uploading of an image, social media cloud automatically compresses the original image to reduce resolution and file size to save storage and provides s

The rapid development of Internet of Vehicles (IoV) and Mobile Edge Computing (MEC) enables vehicles to offload their applications to Roadside Units (RSU). However, without knowledge of vehicles' future locations, wireless connections between vehicles and RSUs are too vulnerable to finish offloading processes. Most existing methods allocate computation tasks statically, ignoring latency between task reception and processing in real IoV environments. Moreover, multiple services running on RSUs limit the availability of resources for offloading which require an efficient allocation of limited available resources. Therefore, this paper addresses the vehicular computation offloading problem by predicting vehicle mobility. We first introduce the Estimated Time of Arrival service into the vehicular MEC architecture to predict vehicles' driving state. Second, we formulate vehicular computation offloading as a dynamic process that efficiently selects the offloading location for each computation task and satisfies the constraints of limited available resources to balance QoS and response fairness. Thirdly, the cooperation among RSUs in our work optimizes the task QoS, but it increases the search space causing a high time consumption. We use the Dynamic Programming algorithm to optimize QoS and response fairness in the cooperative computation offloading problem and propose two offloading algorithms. To obtain the performance of our algorithms close to real IoV environments, we propose a fine-grained simulation method based on Veins. We evaluate our and existing algorithms based on real datasets from Erlangen, Germany, and Shenzhen, China.