Multi-key privacy-preserving deep learning in cloud computing

Li, Ping; Li, Jin; Huang, Zhengan; Li, Tong; Gao, Chongzhi; Yiu, Siu-Ming; Chen, Kai

doi:10.1016/j.future.2017.02.006

Cited by 420 publications

(164 citation statements)

References 24 publications

Supporting

Mentioning

164

Contrasting

Order By: Relevance

“…Data encryption implements privacy protection through applying encryption techniques to the raw data, which can still supports certain computations for learning [24][25][26][27][28][29][30]. Although data encryption has a strong capability to protect privacy, it is at the cost of high computation complexity.…”

Section: Related Workmentioning

confidence: 99%

An information-aware visualization for privacy-preserving accelerometer data sharing

Xiao

Zhao

et al. 2018

Hum. Cent. Comput. Inf. Sci.

View full text Add to dashboard Cite

In the age of big data, plenty of valuable sensing data have been shared to enhance scientific innovation. However, this may cause unexpected privacy leakage. Although numerous privacy preservation techniques, such as perturbation, encryption, and anonymization, have been proposed to conceal sensitive information, it is usually at the cost of the application utility. Moreover, most of the existing works did not distinguished the underlying factors, such as data features and sampling rate, which contribute differently to utility and privacy information implied in the shared data. To well balance the application utility and privacy leakage for data sharing, we utilize mutual information and visualization techniques to analyze the impact of the underlying factors on utility and privacy, respectively, and design an interactive visualization tool to help users identify the appropriate solution to achieve the objectives of high application utility and low privacy leakage simultaneously. To illustrate the effectiveness of the proposed scheme and tool, accelerometer data collected from mobile devices have been adopted as an illustrative example. Experimental study has shown that feature selection and sampling frequency play dominant roles in reducing privacy leakage with much less reduction on utility, and the proposed visualization tool can effectively recommend the appropriate combination of features and sampling rates that can help users make decision on the trade-off between utility and privacy.

show abstract

Section: Related Workmentioning

confidence: 99%

An information-aware visualization for privacy-preserving accelerometer data sharing

Xiao

Zhao

et al. 2018

Hum. Cent. Comput. Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…Meanwhile, this scheme did not depend on public key infrastructure (PKI) [31]. Later, Li et al introduced a new PBS, which was also constructed on bilinear pairings; it was independent of PKI [32]. However, these schemes are inefficient and are not proven to be secure.…”

Section: Idpbs Schemes Based On Bilinearmentioning

confidence: 99%

An Efficient Identity‐Based Proxy Blind Signature for Semioffline Services

Zhu

Tan

Zhu

et al. 2018

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Fog computing extends the cloud computing to the network edge and allows deploying a new type of semioffline services, which can provide real-time transactions between two entities, while the central cloud server is offline and network edge devices are online.For an e-payment system and e-voting with such feature, proxy blind signature is a cornerstone to protect users' privacy. However, the signature based on number theorem, such as hard mathematical problems on factoring problem, discrete logarithm problem, and bilinear pairings, cannot defeat quantum computers attack. Meanwhile, these schemes need to depend on complex public key infrastructure. Thus, we construct an identity-based proxy blind signature scheme based on number theorem research unit lattice, which can defeat quantum computers attack and does not need to depend on public key infrastructure. The security of the proposed scheme is dependent on Ring-Small Integer Solution problem over number theorem research unit lattice. The proposed scheme meets the properties of blind signature and proxy signature. Then we compare the proposed scheme with other existing proxy blind signature schemes; the result shows that the proposed scheme outperforms ZM scheme except in proxy signer's signature size and can be more secure than TA scheme and MMHP scheme.

show abstract

“…Network virtualization is one of the main technologies and promoters of edge-of-things computing. Network virtualization allows multiple heterogeneous virtual networks (VNs) to share the same physical network in edge-of-things computing [12][13][14][15][16]. Due to the increasing popularity of edge-ofthings computing, a great deal of research has been conducted on network virtualization and virtual network mapping technology [17][18][19][20][21][22][23][24].…”

Section: Introductionmentioning

confidence: 99%

Reliable design for virtual network requests with location constraints in edge-of-things computing

Zhang

Sangaiah

2018

J Wireless Com Network

View full text Add to dashboard Cite

How to efficiently map virtual networks (VNs) onto a shared physical network is a challenging issue in the field of network virtualization in edge-of-things computing. Since an efficient VN mapping approach can reduce network resource consumption, lower latency, and enhance service reliability, it is important for both customers and network service providers. In this paper, we study the problem of mapping multiple VNs with geographic location constraints onto a physical network while considering the survivability and reliability requirements of each VN request in edge-ofthings based data centers. We present the model of this problem and propose a Geographic-Guided Survivable Multiple VN Mapping (GG-SMVNM) algorithm to efficiently solve this problem, which simultaneously considers resource sharing and mapping VN links and nodes in edge-of-things computing. Furthermore, we conduct a large amount of simulations to validate and evaluate our proposed approach. The simulation results show that the proposed method is superior to the existing solution.

show abstract

Multi-key privacy-preserving deep learning in cloud computing

Cited by 420 publications

References 24 publications

An information-aware visualization for privacy-preserving accelerometer data sharing

An information-aware visualization for privacy-preserving accelerometer data sharing

An Efficient Identity‐Based Proxy Blind Signature for Semioffline Services

Reliable design for virtual network requests with location constraints in edge-of-things computing

Contact Info

Product

Resources

About