Autonomous vehicles (AVs) are increasingly common, although there remain a number of limitations that need to be addressed in order for their deployment to be more widespread. For example, to mitigate the failure of self-driving functions in AVs, introducing the remote control capability (which allows a human driver to operate the vehicle remotely in certain circumferences) is one of several countermeasures proposed. However, the remote control capability breaks the isolation of onboard driving systems and can be potentially exploited by malicious actors to take over control of the AVs; thus, risking the safety of the passengers and pedestrians (e.g., AVs are remotely taken over by terrorist groups to carry out coordinated attacks in places of mass gatherings). Therefore, security is a key, mandatory feature in the design of AVs. In this paper, we propose a cloud-centric three-factor authentication and key agreement protocol (CT-AKA) integrating passwords, biometrics and smart cards to ensure secure access to both cloud and AVs. Three typical biometric encryption approaches, including fuzzy vault, fuzzy commitment, and fuzzy extractor, are unified to achieve three-factor authentication without leaking the biometric privacy of users. Moreover, two session keys are negotiated in our protocol, namely: one between the user and AV to support secure remote control of the AV, and the other is negotiated between the mobile device and the cloud to introduce resilience to the compromise of ephemeral security parameters to ensure cloud data access security with a high security guarantee. Finally, we formally verify the security properties and evaluate the efficiency of CT-AKA, whose findings demonstrate that the protocol achieves high security strength with reasonable computation and communication costs.

Ciphertext-policy attribute-based encryption (CP-ABE) is widely used in fine-grained access control to realize data security sharing. However, most of the existing CP-ABE access control schemes involve intermediary entities, which might suffer from a high trust-building cost, single point of failure and so on. Due to the decentralization and transparency of blockchain, some blockchain-based access control schemes are proposed to address these problems, but bring new challenges, such as policy and attribute privacy leakage. In this paper, we propose a new trustworthy secure ciphertext-policy and attribute hiding access control scheme based on blockchain, named TrustAccess, to achieve trustworthy access while guaranteeing the privacy of policy and attribute. For one thing, to make the existing hidden policy CP-ABE more efficient and scalable for blockchain, we propose an optimized hidden policy CP-ABE, named HP-CP-ABE, to ensure policy privacy while satisfying large universe access requirement. For another thing, we use ElGamal homomorphic encryption to ensure the attribute privacy during permission verification. Finally, we theoretically prove the effectiveness of our TrustAccess by security analysis from the aspect of blockchain operations and HP-CP-ABE. Comprehensive comparisons and extensive experiments are conducted to demonstrate the advantages of our TrustAccess.

Federated learning (FL) has gained popularity in the field of machine learning, which allows multiple participants to collaboratively learn a highly-accurate global model without exposing their sensitive data. However, FL is susceptible to poisoning attacks, in which malicious clients manipulate local model parameters to corrupt the global model. Existing FL frameworks based on detecting malicious clients suffer from unreasonable assumptions (e.g., clean validation datasets) or fail to balance robustness and efficiency. To address these deficiencies, we propose FedDMC, which implements robust federated learning by efficiently and precisely detecting malicious clients. Specifically, FedDMC first applies principal component analysis to reduce the dimensionality of the model parameters, which retains the primary parameter feature and reduces the computational overhead for subsequent clustering. Then, a binary tree-based clustering method with noise is designed to eliminate the effect of noisy points in the clustering process, facilitating accurate and efficient malicious client detection. Finally, we design a self-ensemble detection correction module that utilizes historical results via exponential moving averages to improve the robustness of malicious client detection. Extensive experiments conducted on three benchmark datasets demonstrate that FedDMC outperforms state-of-the-art methods in terms of detection precision, global model accuracy, and computational complexity.

With the intelligentization of Maritime Transportation System (MTS), Internet of Thing (IoT) and machine learning technologies have been widely used to achieve the intelligent control and routing planning for ships. As an important branch of machine learning, federated learning is the first choice to train an accurate joint model without sharing ships' data directly. However, there are still many unsolved challenges while using federated learning in IoT-enabled MTS, such as the privacy preservation and Byzantine attacks. To surmount the above challenges, a novel mechanism, namely DisBezant, is designed to achieve the secure and Byzantine-robust federated learning in IoT-enabled MTS. Specifically, a credibility-based mechanism is proposed to resist the Byzantine attack in non-iid (not independent and identically distributed) dataset which is usually gathered from heterogeneous ships. The credibility is introduced to measure the trustworthiness of uploaded knowledge from ships and is updated based on their shared information in each epoch. Then, we design an efficient privacy-preserving gradient aggregation protocol based on a secure two-party calculation protocol. With the help of a central server, we can accurately recognise the Byzantine attackers and update the global model parameters privately. Furthermore, we theoretically discussed the privacy preservation and efficiency of DisBezant. To verify the effectiveness of our DisBezant, we evaluate it over three real datasets and the results demonstrate that DisBezant can efficiently and effectively achieve the Byzantine-robust federated learning. Although there are 40% nodes are Byzantine attackers in participants, our DisBezant can still recognise them and ensure the accurate model training.

Deep learning has aroused a lot of attention and has been used successfully in many domains. Generally, the training of models requires large, representative datasets, which may be collected from a large number of users and contain sensitive information. The collected data would be stored and computed by service providers (SPs) or delegated to an untrusted cloud. Users can neither control how it will be used, nor realize what will be learned, which make the privacy issues prominent and severe. To solve the privacy issues, one of the most popular approaches is to encrypt their data. However, this technique inevitably leads to another challenge that how to train the model based on multi-key encrypted data. In this paper, we propose a novel privacy-preserving learning model, namely PDLM, to apply deep learning over the multi-key encrypted data. In PDLM, users contribute their encrypted data to SP to learn a specific model. We adopt an effective privacy-preserving calculation toolkit to achieve the training in a privacy-preserving manner. Finally, we conduct the analysis of PDLM in both theory and practice and the experimental results over two real-world datasets demonstrate that our PDLM can effectively and efficiently train the model in a privacy-preserving way.

Cloud computing, which provides a brand-new service model, has become an important infrastructure in the information age, and has been widely used in numerous fields. The Key-Policy Attribute-Based Encryption (KP-ABE) scheme allows the encrypted data with fine-grained access control in the cloud environment. However, achieving large-scale user revocation in the application scenario of KP-ABE becomes one of the thorny problems. Furthermore, the computation and communication costs of the previous user revocation schemes were generally high, especially when a large number of users were revoked. To address these problems, an enhanced high-performance user-revocable KP-ABE scheme combined with the puncture method was proposed. In this article, the user could be revoked by the fine-grained restriction policy. When revoking the user, the cloud would run the puncture algorithm to embed the restriction policy defined by the data owner into the ciphertext. This method could effectively omit the re-encryption and key updating processes, by which the computation and communication overhead of the user revocation are efficiently reduced, and the user revocation becomes more flexible and efficient. Moreover, the Chosen-Plaintext Attack (CPA) security proof and extensive simulation results demonstrate the reliability and efficiency of the proposed scheme for user revocation in a cloud environment.