Cross-modal search with deep learning shows an attractive potential on heterogeneous data sets due to its accuracy and effectiveness. Usually, it has to aggregate and train large amounts of data to make precise predictions, which is feasible in the single-user environment and plaintext areas. However, the challenge lies in maintaining search accuracy within a multiuser environment while simultaneously safeguarding user data privacy. In this article, we address these challenges by centering on the development of secure cross-modal search techniques that are supported by federated learning. To our knowledge, this marks the first endeavor to execute cross-modal encrypted data search through the auspices of federated learning. Our approach specifically employs a secure and reliable federated learning technique to extract key features from diverse heterogeneous data, ensuring precise model training in a distributed data environment. Consequently, while the data is encrypted, it achieves the protection of data privacy and simultaneously enhances the efficiency and accuracy of cross-modal search. To further enhance retrieval efficiency, we propose a tag classification algorithm that employs homomorphic encryption and locality-sensitive hashing. Furthermore, we design a secure method for calculating Euclidean distance that utilizes the k-nearest neighbor algorithm. This method efficiently identifies the result nearest to the query data, thereby enhancing the accuracy of the search results. Both theoretical analysis and experimental evaluation demonstrate that our proposed scheme not only protects user data privacy but also has high accuracy and efficiency.

As a useful cryptographic primitive, searchable symmetric encryption (SSE) has been intensively studied to achieve the secure and efficient retrieval of encrypted data. In order to process update operations, dynamic SSE schemes have been proposed. But recently, file-injection attack has threatened the security of traditional dynamic SSE protocols. Therefore, designing dynamic SSE schemes with forward privacy becomes a new demand to resist the above attack. Meanwhile, multi-client setting is another requirement in SSE techniques where multiple clients can be delegated and have access to the database. However, most of previous forward private schemes were constructed for single-client setting and cannot directly extended to multi-client environment efficiently. To solve the problem, we propose a forward private SSE scheme with support for multi-client in cloud computing. The proposed scheme is based on XOR-homomorphic function and involves two new data structures as private link and public search tree. Security proof demonstrates the proposed scheme can meet the desired secure features. We then conduct experimental evaluation of the proposed scheme and make comparison with related schemes. The result shows that the proposed scheme tends to have high efficiency.

Vehicular ad hoc network (VANETs) plays a major part in intelligent transportation to enhance traffic efficiency and safety. Security and privacy are the essential matters needed to be tackled due to the open communication channel. Most of the existing schemes only provide message authentication without identity authentication, especially the inability to support forward secrecy which is a major security goal of authentication schemes. In this article, we propose a privacy-preserving mutual authentication scheme with batch verification for VANETs which support both message authentication and identity authentication. More importantly, the proposed scheme achieves forward secrecy, which means the exposure of the shared key will not compromise the previous interaction. The security proof shows that our scheme can withstand various known security attacks, such as the impersonation attack and forgery attack. The experiment analysis results based on communication and computation cost demonstrate that our scheme is more efficient compared with the related schemes.

Content-sharing is one of the major applications of vehicular networks. To fully utilize the spectrum and the connection time, rate-compatible codes are required when sharing content. In this paper, we present a simple and flexible method to construct low-complexity rate-compatible codes for content sharing. We first present a novel construction framework for rate-compatible codes via recursive block Markov superposition transmission (rBMST). In the proposed construction, the shared content is partitioned into equal-length data chunks and transmitted directly, while their replicas are taken as the inputs of a given number of parallel systematic encoders to generate parity-check chunks. These parity-check chunks are then transmitted in parallel in a recursive block Markov superposition transmission manner. The proposed construction is flexible in the sense that codes with arbitrary rates can be obtained by adjusting the number of parallel rBMST encoders and the number of randomly punctured bits. We show that the simplest construction, using repetition to generate the parity-check chunks, leads to high-performance and low-complexity rate-compatible rBMST (RC-rBMST) codes. Specifically, the extrinsic information transfer (EXIT) chart analysis shows that asymptotic thresholds of the repetition-based RC-rBMST (RB-RC-rBMST) codes are within 0.25 dB of the channel capacities for a wide range of coding rates. Numerical results are presented to confirm the advantages of the RB-RC-rBMST codes in performance and complexity. Particularly, the RB-RC-rBMST codes perform as well as BMST-R codes but with much lower computational complexities.

With the rapid development of network and storage technology, cloud storage has become a new service mode, while data sharing and user revocation are important functions in the cloud storage. Therefore, according to the characteristics of cloud storage, a revocable key-aggregate encryption scheme is put forward based on subset-cover framework. The proposed scheme not only has the key-aggregate characteristics, which greatly simplifies the user’s key management, but also can revoke user access permissions, realizing the flexible and effective access control. When user revocation occurs, it allows cloud server to update the ciphertext so that revoked users can not have access to the new ciphertext, while nonrevoked users do not need to update their private keys. In addition, a verification mechanism is provided in the proposed scheme, which can verify the updated ciphertext and ensure that the user revocation is performed correctly. Compared with the existing schemes, this scheme can not only reduce the cost of key management and storage, but also realize user revocation and achieve user’s access control efficiently. Finally, the proposed scheme can be proved to be selective chosen-plaintext security in the standard model.