Nowadays, more individuals and corporations tend to use machine learning as a service (MLaaS) in cloud computing environment. However, when enjoying the pay-as-you-go mode and flexible capacity of cloud computing, it also increases the risk of privacy leakage for sensitive data. In this paper, we aim to efficiently implement privacy-preserving MLaaS, and focus on k-means clustering over outsourced encrypted cloud databases. Previous works mainly utilize partially homomorphic encryptions, which require a great number of interactive protocols with high computation and communication costs, making them not practical in real-world applications. To better solve this problem, we propose a new secure and efficient outsourced k-means clustering (SEOKC) scheme using fully homomorphic encryption with ciphertext packing technique, which achieves parallel computation without extra cost. The proposed scheme preserves privacy in three aspects: (1) database security, (2) privacy of clustering results and (3) hiding of data access patterns. We provide formal security analysis and evaluate the performance of the proposed scheme through extensive experiments. The experiment results show that our scheme needs much less computation cost (more than three orders of magnitude lower) than the state-of-the-art schemes, and is suitable to be applied on large databases.

Over the years, the flourish of crowd computing has enabled enterprises to accomplish computing tasks through crowdsourcing in a large-scale and high-quality manner, and therefore how to efficiently and securely implement crowd computing becomes a hotspot. Some recent work innovatively adopted a P2P (peer-to-peer) network as the communication environment of crowdsourcing. Based on its decentralized control, issues like single-point-of-failure or DDoS attack can be overcome to some extent, but the huge computing capacity and storage costs required by this scheme is always unbearable. Federated learning is a distributed machine learning that supports local storage of data, and clients implement training through interactive gradient values. In our work, we combine blockchain with federated learning and propose a crowdsourcing framework named CrowdSFL, that users can implement crowdsourcing with less overhead and higher security. In addition, to protect the privacy of participants, we design a new re-encryption algorithm based on Elgamal to ensure that interactive values and other information will not be exposed to other participants outside the workflow. Finally, we have proved through experiments that our framework is superior to some similar work in accuracy, efficiency, and overhead.

The flourishing deep learning on distributed training datasets arouses worry about data privacy. The recent work related to privacy-preserving distributed deep learning is based on the assumption that the server and any learning participant do not collude. Once they collude, the server could decrypt and get data of all learning participants. Moreover, since the private keys of all learning participants are the same, a learning participant must connect to the server via a distinct TLS/SSL secure channel to avoid leaking data to other learning participants. To fix these problems, we propose a privacy-preserving distributed deep learning scheme with the following improvements: (1) no information is leaked to the server even if any learning participant colludes with the server; (2) learning participants do not need different secure channels to communicate with the server; and (3) the deep learning model accuracy is higher. We achieve them by introducing a key transform server and using homomorphic re-encryption in asynchronous stochastic gradient descent applied to deep learning. We show that our scheme adds tolerable communication cost to the deep learning system, but achieves more security properties. The computational cost of learning participants is similar. Overall, our scheme is a more secure and more accurate deep learning scheme for distributed learning participants.

The emerging cloud-based IoT paradigm enables IoT devices to directly upload their collected data to the remote cloud and allows data owners to conveniently manage those data through cloud APIs, which has greatly reduced infrastructure investment and data management cost in many IoT applications. Considering that the outsourced data is out of the physical control of data owners and the cloud server cannot always be fully trusted, how to securely delete the unneeded sensitive data stored in cloud to prevent potential data leakage issues is a big challenge. Most of the existing solutions only support coarse-grained deletion and rely on the participation of the cloud server, so their flexibility and practicability are seriously restricted. In this paper, based on an enhanced policy-based puncturable encryption (P-PUN-ENC) primitive, we propose a secure and fine-grained self-controlled outsourced data deletion scheme in cloud-based IoT. The main contribution of our scheme is that it enables data owners to precisely and permanently delete their outsourced IoT-driven data in a policy-based way without relying on the cloud server. To achieve this, we subtly utilize the logical relationship between puncture policy and access policy, and design a policy transform method to convert the puncture process based on puncture policies into update process of access policies. Then, we utilize key delegation technique in attribute-based encryption (ABE) to complete the corresponding key update operations. Additionally, to address the issue of growing key storage and decryption cost in P-PUN-ENC, we propose the outsourced policy-based puncturable encryption (OP-PUN-ENC) primitive by combining the key and decryption outsource technique with P-PUN-ENC. Comprehensive comparisons show that our proposed scheme can better meet the data deletion requirements in cloud-based IoT, and formal security proof and extensive simulation results demonstrate the reliability and efficiency of the proposed scheme.

Cloud-assisted Internet of Medical Things (IoMT) is becoming an emerging paradigm in the healthcare domain, which involves collection, storage and usage of the medical data. Considering the confidentiality and accessibility of the outsourced data, secure and fine-grained data sharing is a crucial requirement for the patients. Attribute-based encryption (ABE) is a promising solution to deal with this issue, but considering its property of each attribute sharing with multiple users, how to flexibly and efficiently update access privileges of certain users without affecting others is still a serious challenge. In this article, we propose a secure and fine-grained data sharing scheme with flexible user access privilege update in cloud-assisted IoMT environment. Specifically, we take ABE as the basic building block, and utilize proxy re-encryption and key blinding techniques to empower the cloud server to re-encrypt the ciphertext affected by revocation and update keys for unrevoked users. In addition, adding attributes for users to extend their access rights is realized only based on few key components stored in cloud without entirely re-computing and re-issuing keys for them. As a result, the patients are able to flexibly and efficiently share their data and manage users’ privileges. Formal proof and detailed performance evaluation demonstrate the security and efficiency of the proposed scheme.

Access control in Internet of Things (IoT) systems has long been facing with single-point-of-failure, collusion and other security issues. Deploying most of the access control procedures on blockchain makes it more trustworthy. However, the miscellaneous transaction data on the public blockchain incurs an extra burden on computing and communication overhead, which hinders its application for IoT devices. Additionally, the demands of rapid response in industrial IoT scenarios (e.g., edge computing scenarios) is hardly realized under a public blockchain. In this paper, we propose an IoT-applicable access control model under an original double-layer blockchain architecture, in which the mortgage/registration and control processes can be disaggregated. Depending on this architecture, the communication overhead for IoT devices is reduced and a rapid response is achieved. With linear secret sharing scheme, attribute-based access policies for resource objects are established to ensure fine-grained access control. We further implement a smart contract prototype on Ethereum and Fisco Bcos. Extensive experiments and numerical analysis demonstrate the feasibility of our proposed model.