Deep learning can achieve higher accuracy than traditional machine learning algorithms in a variety of machine learning tasks. Recently, privacy-preserving deep learning has drawn tremendous attention from information security community, in which neither training data nor the training model is expected to be exposed. Federated learning is a popular learning mechanism, where multiple parties upload local gradients to a server and the server updates model parameters with the collected gradients. However, there are many security problems neglected in federated learning, for example, the participants may behave incorrectly in gradient collecting or parameter updating, and the server may be malicious as well. In this paper, we present a distributed, secure, and fair deep learning framework named \textit{DeepChain} to solve these problems. DeepChain provides a value-driven incentive mechanism based on Blockchain to force the participants to behave correctly. Meanwhile, DeepChain guarantees data privacy for each participant and provides auditability for the whole training process. We implement a DeepChain prototype and conduct experiments on a real dataset for different settings, and the results show that our DeepChain is promising.

Crowdsourcing systems which utilize the human intelligence to solve complex tasks have gained considerable interest and adoption in recent years. However, the majority of existing crowdsourcing systems rely on central servers, which are subject to the weaknesses of traditional trust-based model, such as single point of failure. They are also vulnerable to distributed denial of service (DDoS) and Sybil attacks due to malicious users involvement. In addition, high service fees from the crowdsourcing platform may hinder the development of crowdsourcing. How to address these potential issues has both research and substantial value. In this paper, we conceptualize a blockchain-based decentralized framework for crowdsourcing named CrowdBC, in which a requester's task can be solved by a crowd of workers without relying on any third trusted institution, users' privacy can be guaranteed and only low transaction fees are required. In particular, we introduce the architecture of our proposed framework, based on which we give a concrete scheme. We further implement a software prototype on Ethereum public test network with real-world dataset. Experiment results show the feasibility, usability and scalability of our proposed crowdsourcing system.

Load frequency control (LFC) is widely employed to keep smart grids stable and secure. This paper proposes an adaptive resilient LFC scheme for sub-systems of smart grids under denial-of-service (DoS) attacks with energy constraint. Firstly, a resilient triggering communication scheme is introduced, where the triggering condition includes the uncertainty item induced by DoS attacks. Secondly, an adaptive resilient event-triggering LFC scheme is proposed to further reduce the communication burden and defeat the DoS attacks, where the event-triggering parameter can be dynamically adjusted. Third, a stability criterion is derived for Proportional Integral-based LFC systems by employing Lyapunov theory. Finally, to validate the proposed control scheme, case studies are carried out based on three different LFC power generation systems including one-area, two-area and three-area models. The simulation results clearly demonstrate that the proposed adaptive resilient LFC scheme can reduce the communication burden while defeating DoS attacks by comparing with resilient event-triggering LFC scheme and event-triggering LFC scheme in term of defense effect and average triggering period.

Commercial advertisement (ad) dissemination has been proliferating on connected vehicles, allowing users to promote their products via vehicle-to-vehicle/-infrastructure communications. Despite the prospect of ad dissemination in vehicular networks, it faces challenges upon deployment especially on security and privacy. Particularly, vehicles may collude to defraud the advertiser to obtain rewards without disseminating ads, which may cause unfair “free-riding” issue in these activities. Furthermore, concerns on possible privacy leakage may discourage vehicles to participate in the process of ad dissemination. In addition, external DDoS attacks and internal single point of failure may also affect service availability. To address these issues, we explore the potential of blockchain technology to construct a fair and anonymous scheme for advertising in vehicular networks. We first present the overview of the blockchain-based ad dissemination framework. Then, under the framework, we design a concrete, fair and anonymous scheme. To ensure fairness, we utilize the Merkle hash tree together with smart contracts to achieve the “proof-of-ad-receiving” property (i.e., check whether a vehicle indeed receives an ad without deception or introducing significant storage cost) to mitigate the “free-riding” attack. On the other hand, any ad receiver who acquires a dissemination reward per ad more than once can be effectively detected and will be punished which is achieved by using smart contracts. Additionally, the proposed scheme can protect vehicles' privacy in terms of anonymity and conditional unlinkability based on zero-knowledge proof techniques. Lastly, extensive security analysis and implementations demonstrate the feasibility and efficiency of the scheme.

Federated learning (FL) trains a model over multiple datasets by collecting the local models rather than raw data, which can help facilitate distributed data analysis in many real-world applications. Since the model parameters can leak information about the training datasets, it is necessary to preserve the privacy of the FL participants' local models. Furthermore, FL is vulnerable to poisoning attacks which can significantly decrease the model utility. To settle the above issues, we propose a privacy-preserving and Byzantine-robust FL scheme $\Pi _{\rm{P2Brofl}}$ that maintains robustness in the presence of poisoning attacks and preserves the privacy of local models simultaneously. Specifically, $\Pi _{\rm{P2Brofl}}$ leverages three-party computation (3PC) to securely achieve a Byzantine-robust aggregation method. To improve the efficiency of privacy-preserving local model selection and aggregation, we propose a maliciously secure top- $k$ protocol $\Pi _{\rm{top}-k}$ that has low communication overhead. Moreover, we present an efficient maliciously secure shuffling protocol $\Pi _{\rm{shuffle}}$ since secure shuffling is necessary for our secure top- $k$ protocol. The security proof of the scheme is given and experiments on real-world datasets are conducted in this paper. When the proportion of Byzantine participants is 50%, the error rate of the model only increases by 1.05% while it increases by 23.78% without using our protection.

We propose a new approach for privacy-preserving and verifiable convolutional neural network (CNN) testing in a distrustful multi-stakeholder environment. The approach is aimed to enable that a CNN model developer convinces a user of the truthful CNN performance over non-public data from multiple testers , while respecting model and data privacy. To balance the security and efficiency issues, we appropriately integrate three tools with the CNN testing, including collaborative inference, homomorphic encryption (HE) and zero-knowledge succinct non-interactive argument of knowledge (zk-SNARK). We start with strategically partitioning a CNN model into a private part kept locally by the model developer, and a public part outsourced to an outside server. Then, the private part runs over the HE-protected test data sent by a tester, and transmits its outputs to the public part for accomplishing subsequent computations of the CNN testing. Second, the correctness of the above CNN testing is enforced by generating zk-SNARK based proofs, with an emphasis on optimizing proving overhead for two-dimensional (2-D) convolution operations, since the operations dominate the performance bottleneck during generating proofs. We specifically present a new quadratic matrix program (QMP)-based arithmetic circuit with a single multiplication gate for expressing 2-D convolution operations between multiple filters and inputs in a batch manner. Third, we aggregate multiple proofs with respect to a same CNN model but different testers’ test data ( i.e ., different statements) into one proof, and ensure that the validity of the aggregated proof implies the validity of the original multiple proofs. Lastly, our experimental results demonstrate that our QMP-based zk-SNARK performs nearly 13.9× faster than the existing quadratic arithmetic program (QAP)-based zk-SNARK in proving time, and 17.6× faster in Setup time, for high-dimension matrix multiplication. Besides, the limitation on handling a bounded number of multiplications of QAP-based zk-SNARK is relieved.