With the proliferation of machine learning, the cloud server has been employed to collect massive data and train machine learning models. Several privacy-preserving machine learning schemes have been suggested recently to guarantee data and model privacy in the cloud. However, these schemes either mandate the involvement of the data owner in model training or utilize high-cost cryptographic techniques, resulting in excessive computational and communication overheads. Furthermore, none of the existing work considers the malicious behavior of the cloud server during model training. In this paper, we propose the first privacy-preserving and verifiable support vector machine training scheme by employing a two-cloud platform. Specifically, based on the homomorphic verification tag, we design a verification mechanism to enable verifiable machine learning training. Meanwhile, to improve the efficiency of model training, we combine homomorphic encryption and data perturbation to design an efficient multiplication operation for the encryption domain. A rigorous theoretical analysis demonstrates the security and reliability of our scheme. The experimental results indicate that our scheme can reduce computational and communication overheads by at least 43.94% and 99.58%, respectively, compared to state-of-the-art SVM training methods.

Incentive plays an important role in knowledge discovery, as it impels users to provide high-quality knowledge. To promise incentive schemes with transparency, blockchain technology has been widely used in incentive schemes. Currently, privacy, reliability, streamlined processing, and quality awareness are major challenges in designing blockchain-based incentive schemes. In this paper, we design a blockchain-based eFficient and pRivacy-preserving qUality-aware IncenTive scheme called FRUIT. With well-designed smart contracts, FRUIT achieves privacy, reliability, streamlined processing, and quality awareness during the whole procedure. Specifically, we design a novel lightweight encryption method by combining matrix decomposition with proxy re-encryption and a privacy-preserving task allocation based on the polynomial fitting function and hash function. Then, we leverage our proposed lightweight encryption and task allocation to build an efficient and privacy-preserving knowledge discovery protocol in order to securely calculate the data quality and truthful knowledge. To promise user reliability in the incentive scheme, we utilize the Dirichlet distribution to realize the automatic reputation prediction based on the data quality by deploying the reputation management on the blockchain. Moreover, we also deploy the payment management on the blockchain, endowing the incentive scheme to reward participants based on the data quality automatically. Through a detailed security analysis, we demonstrate that data privacy and task privacy are well preserved during the whole process. Theoretical analysis and extensive experiments on real-world datasets demonstrate that FRUIT has acceptable efficiency and affordable performance in terms of computation cost, communication overhead, and gas consumption.

The neural network has been widely used to train predictive models for applications such as image processing, disease prediction, and face recognition. To produce more accurate models, powerful third parties (e.g., clouds) are usually employed to collect data from a large number of users, which however may raise concerns about user privacy. In this paper, we propose an Efficient and Privacy-preserving Neural Network scheme, named EPNN, to deal with the privacy issues in cloud-based neural networks. EPNN is designed based on a two-cloud model and techniques of data perturbation and additively homomorphic cryptosystem. This scheme enables two clouds to cooperatively perform neural network training and prediction in a privacy-preserving manner and significantly reduces the computation and communication overhead among participating entities. Through a detailed analysis, we demonstrate the security of EPNN. Extensive experiments based on real-world datasets show EPNN is more efficient than existing schemes in terms of computational costs and communication overhead.

Mobile crowdsensing has emerged as a popular platform to solve many challenging problems by utilizing users’ wisdom and resources. Due to user diversity, the data provided by different individuals may vary significantly, and thus it is important to analyze data quality during data aggregation. Truth discovery is effective in capturing data quality and obtaining accurate mobile crowdsensing results. Existing works on truth discovery either cannot protect both task privacy and data privacy, or introduce tremendous computational costs. In this paper, we propose an efficient and strong privacy-preserving truth discovery scheme, named EPTD, to protect users’ task privacy and data privacy simultaneously in the truth discovery procedure. In EPTD, we first exploit the randomizable matrix to express users’ tasks and sensory data. Then, based on the matrix computation properties, we design key derivation and (re-)encryption mechanisms to enable truth discovery to be performed in an efficient and privacy-preserving manner. Through a detailed security analysis, we demonstrate that data privacy and task privacy are well preserved. Extensive experiments based on real-world and simulated mobile crowdsensing applications show EPTD has practical efficiency in terms of computational cost and communication overhead.

Blockchain has been a promising infrastructure for enabling secure data sharing for the Internet of Things (IoT). With the widespread of IoT applications, security issues such as data privacy, anonymity, and accountability become critical concerns for the users, which are essential principles for secure communication in those applications. However, the existing blockchain-based data sharing schemes mainly consider data privacy. Only a few works can support anonymity with strong, trusted assumptions. Thus, there is a research gap on the anonymity of blockchain-based data sharing for IoT, which does not rely on any trusted party. In this paper, we propose a blockchain-based anonymous data sharing scheme (BA-DS) by adopting a novel public key encryption derived from a ring signature. In BA-DS, we remove the trusted party and ensure anonymity by using an unconditional linkable ring signature and signature of knowledge (SoK). During the revocation, we apply blockchain infrastructure to record the valid revocation list and generate a tag for data stored on the cloud, providing solid accountability. The formal security analysis shows that BA-DS is selective indistinguishable secure in the random oracle model. Additionally, we also prove that BA-DS holds anonymity, data privacy, accountability, and authenticity. The extensive experiments indicate that our proposed BA-DS achieves reasonable efficiency in terms of computational complexity, communication overhead, and consumption on the blockchain.

Outsourcing storage has emerged as an effective solution to manage the increasing volume of data. With the popularity of pay-as-you-go payment models in outsourcing storage, data auditing schemes that prioritize timeliness can be valuable evidence for elastic bill settlement. Unfortunately, existing data auditing schemes do not sufficiently consider timeliness during auditing. Furthermore, practical data auditing schemes should have the capability to check the integrity of scalable data. In this paper, we propose a blockchain-based dynamic data auditing scheme with strong timeliness to ensure that data stored in outsourcing storage systems remain intact. Our scheme encapsulates timestamps into homomorphic verifiable tags to simultaneously check data integrity and timestamp validity. To achieve dynamicity, we utilize the Merkle hash tree to store the tags, allowing for block-level dynamic operations. Additionally, by leveraging the transparency, non-repudiation, and tamper resistance of blockchain technology, we design a blockchain-based data auditing framework to prevent malicious behavior from all entities. We then formally prove the soundness and privacy of our scheme. Finally, we conduct theoretical analysis and experimental evaluation to demonstrate that the performance of our scheme is of acceptable efficiency to existing works in terms of computation cost, communication overhead, and storage overhead.