arXiv subjects

Ruihui Zhao

Publications and source records attributed to Ruihui Zhao.

22 records · Page 2Linked to original sources

arXiv2020

Towards Communication-efficient and Attack-Resistant Federated Edge Learning for Industrial Internet of Things

Federated Edge Learning (FEL) allows edge nodes to train a global deep learning model collaboratively for edge computing in the Industrial Internet of Things (IIoT), which significantly promotes the development of Industrial 4.0. However, FEL faces two critical challenges: communication overhead and data privacy. FEL suffers from expensive communication overhead when training large-scale multi-node models. Furthermore, due to the vulnerability of FEL to gradient leakage and label-flipping attacks, the training process of the global model is easily compromised by adversaries. To address these challenges, we propose a communication-efficient and privacy-enhanced asynchronous FEL framework for edge computing in IIoT. First, we introduce an asynchronous model update scheme to reduce the computation time that edge nodes wait for global model aggregation. Second, we propose an asynchronous local differential privacy mechanism, which improves communication efficiency and mitigates gradient leakage attacks by adding well-designed noise to the gradients of edge nodes. Third, we design a cloud-side malicious node detection mechanism to detect malicious nodes by testing the local model quality. Such a mechanism can avoid malicious nodes participating in training to mitigate label-flipping attacks. Extensive experimental studies on two real-world datasets demonstrate that the proposed framework can not only improve communication efficiency but also mitigate malicious attacks while its accuracy is comparable to traditional FEL frameworks.

cs.LG↗

arXiv2017

A Privacy-preserving Community-based P2P OSNs Using Broadcast Encryption Supporting Recommendation Mechanism

Online Social Networks (OSNs) have become one of the most important activities on the Internet, such as Facebook and Google+. However, security and privacy have become major concerns in existing C/S based OSNs. In this paper, we propose a novel scheme called a Privacy-preserving Community-based P2P OSNs Using Broadcast Encryption Supporting Recommendation Mechanism (PCBE) that supports cross-platform availability in stringent privacy requirements. For the first time, we introduce recommendation mechanism into a privacy-preserving P2P based OSNs, in which we firstly employ the Open Directory Project to generate user interest model. We firstly introduce broadcast encryption into P2P community-based social networks together with reputation mechanism to decrease the system overhead. We formulate the security requirements and design goals for privacy- preserving P2P based OSNs supporting recommendation mechanism. The RESTful web-services help to ensure cross-platform availability and transmission security. As a result, thorough security analysis and performance evaluation on experiments demonstrate that the PCBE scheme indeed accords with our proposed design goals.

cs.CR↗

arXiv2017

LRSE: A Lightweight Efficient Searchable Encryption Scheme using Local and Global Representations

Cloud computing is emerging as a revolutionary computing paradigm, while security and privacy become major concerns in the cloud scenario. For which Searchable Encryption (SE) technology is proposed to support efficient retrieval of encrypted data. However, the absence of lightweight ranked search with higher search quality in a harsh adversary model is still a typical shortage in existing SE schemes. In this paper, we propose a novel SE scheme called LRSE which firstly integrates machine learning methods into the framework of SE and combines local and global representations of encrypted cloud data to achieve the above design goals. In LRSE, we employ an improved secure kNN scheme to guarantee sufficient privacy protection. Our detailed security analysis shows that LRSE satisfies our formulated privacy requirements. Extensive experiments performed on benchmark datasets demonstrate that LRSE indeed achieves state-of-the-art search quality with lowest system cost.

cs.IR↗

arXiv2017

Lightweight Efficient Multi-keyword Ranked Search over Encrypted Cloud Data using Dual Word Embeddings

Cloud computing is emerging as a revolutionary computing paradigm which pro-vides a flexible and economic strategy for data management and resource sharing. Security and privacy become major concerns in the cloud scenario, for which Searchable Encryption (SE) technology is proposed to support efficient retrieval of encrypted data. However, the absence of lightweight ranked search is still a typical shortage in existing SE schemes. In this paper, we propose a Lightweight Efficient Multi-keyword Ranked Search over Encrypted Cloud Data using Dual Word Embeddings (LRSE) scheme that supports top-k retrieval in the known background model. For the first time, we formulate the privacy issue and design goals for lightweight ranked search in SE. We employ word embedding trained on the whole English Wikipedia using word2vec to replace the general dictionary, afterwards we make use of Dual Embedding Space Model (DESM) to substitute traditional Vector Space Model (VSM), based on which we achieve the goal of lightweight ranked search with higher precision and solve the challenging prob-lems caused by updating the traditional dictionary in existing SE schemes. In LRSE, we employ an improved secure kNN scheme to guarantee sufficient pri-vacy protection. Our security analysis shows that LRSE satisfies our formulated privacy requirements and extensive experiments performed on real-world datasets demonstrate that LRSE indeed accords with our proposed design goals.

cs.IR↗