Conventional federated learning (FL) approaches generally rely on a centralized server, and there has been a trend of designing asynchronous FL approaches for distributed applications partly to mitigate limitations associated with conventional (synchronous) FL approaches (e.g., single point of failure / attack). In this paper, we first introduce two new tools, namely: a quality-based aggregation method and an extended dynamic contribution broadcast encryption (DConBE). Building on these two new tools and local differential privacy, we then propose a privacy-preserving and reliable decentralized FL scheme, designed to support batch joining/leaving of clients while incurring minimal delay and achieving high model accuracy. In other words, our scheme seeks to ensure an optimal trade-off between model accuracy and data privacy, which is also demonstrated in our simulation results. For example, the results show that our aggregation method can effectively avoid low-quality updates in the sense that the scheme guarantees high model accuracy even in the presence of bad clients who may submit low-quality updates. In addition, our scheme incurs a lower loss and the extended DConBE only slightly affects the efficiency of our scheme. With the extended dynamic contribution broadcast encryption, our scheme can efficiently support batch joining/leaving of clients.

Group-oriented applications generally involve communications of multiple entities (e.g., users and/or devices) through open networks. Typical requirements of group communications include secrecy, authentication, sender non-repudiation, and sender privacy. However, conventional approaches such as group key agreement and broadcast encryption are generally not designed to achieve all these requirements simultaneously or efficiently. In this paper, we propose a one-round dynamic authenticated asymmetric group key agreement with sender non-repudiation and privacy (DAAGKAwSNP) protocol. A key building block of our DAAGKAwSNP protocol is our proposed batch multi-signature scheme with strong unforgeability. We prove that the DAAGKAwSNP protocol achieves secrecy under chosen ciphertext attacks CCA, assuming the intractability of the computational Diffie-Hellman and k-Bilinear Diffie-Hellman exponent problem. We also evaluate DAAGKAwSNPs performance to demonstrate its utility.

Vehicular cloud computing (VCC) is a network architecture that allows a group of entities (i.e., vehicles/roadside infrastructures) to share their resources with other entities. Task delivery in VCC involves the delegation of computation/storage task from a cloud user to some or all the cloud members within a vehicular cloud (VC) for processing. This process inevitably raises concerns regarding how to protect the confidentiality of the task content and the privacy of vehicles. To tackle these challenges, the establishment of a secure channel for task delivery becomes essential. However, the existing secure channel establishment schemes for task delivery in VCC suffer from a few problems including the reliance on a trusted dealer, sender restriction, recipient un-flexibility, or the ignorance of recipient privacy. In this paper, we propose a novel secure channel establishment scheme for task delivery in VCC. It allows a group of entities close to each other to form a VC dynamically without a trusted dealer and allows any entity to be a cloud user who can flexibly select favorable cloud members within a VC to handle its task. The secure channel established by our scheme not only protects the confidentiality of the content of the task but also the privacy of vehicles. Formal security analysis and simulation validate the security and efficiency of our scheme.

Distributed online social network (DOSN) solves the challenges of single-point failure and user data privacy faced by traditional online social network (OSN). Online discussion group, allowing a user to facilitate the communications with other users, is one of the most important components of (D)OSN. Key management is the key technology to ensure the secure establishment of discussion groups in DOSNs. However, the existing key management schemes for secure discussion group establishment in DOSNs cannot meet the requirements of sender non-restriction, receiver controllability, round optimal, certificate freeness simultaneously. In this paper, we propose a novel key management scheme for secure discussion group establishment in DOSNs. In our scheme, any user could use our key management scheme to initialize a discussion group with a piece of discussion group information. Users who are interested in the group topic contained in the discussion group information can join and leave the discussion group at any time once the discussion group is initialized with one-round communication. Any user/sender can find the users that he/she wants to communicate with by looking up the discussion group information of a discussion group and then send encrypted messages to some or all of the users in the discussion group. Therefore, our scheme achieves sender non-restriction, receiver controllability, round optimal, certificate freeness simultaneously. Security analysis also shows that our scheme achieves confidentiality, authentication, full collusion resistance, known-key security and perfect forward security.

Federated learning (FL) allows multiple users to collaboratively train global machine learning models by keeping their data sets local. However, the existing privacy-preserving FL schemes suffer from several limitations, e.g., loss of accuracy, high communication/computation cost, failure to support dynamic users, and insecurity against collusion attacks. To solve these limitations, we propose a lightweight privacy-preserving FL scheme based on a dual-server architecture. Our scheme involves only lightweight cryptographic operations, i.e., hash and symmetric encryption operations, and it has low communication overhead. Thus, it is computationally lightweight and round-efficient. Further, it allows users to join/quit an FL task and it is accuracy-lossless. We formally prove that our scheme remains secure even in case of collusion attacks. In particular, if an attacker colludes with one of the servers and all the users who participate in an FL task except two, the privacy of user gradients stays unviolated. The reported experimental results demonstrate that our scheme incurs only a marginal increase in total communication overhead compared to the FL scheme without any privacy protection. In terms of computation overhead, the cost per user remains stable as the number of users grows, while the cost for the server is comparable to that of the FL scheme without any privacy protection.

Mobile ad hoc networks (MANETs) are self-configuring networks of wireless nodes, i.e., mobile devices. Since communications in MANETs occur via wireless channels, it is of significance to secure communications among wireless and mobile nodes. Group key management, as a widely used method for securing group communications, has potentially been used in MANETs for years. Most recently, a secure receiver-unrestricted group key management scheme for MANETs has been proposed, which is used to establish a secure channel among a group of wireless nodes without a trusted dealer, which has some advantages such as eliminating the certificate management problem and receiver restriction. However, a formal security analysis of this scheme is still lacking. Therefore, in this paper, we propose the complete security proof to demonstrate that the scheme satisfies the essential security properties including authentication, message confidentiality, known-key security and dynamic secrecy. We also give a brief discussion about the efficiency of the scheme.