Differentially-Private and Trustworthy Online Social Multimedia Big Data Retrieval in Edge Computing

Pan Zhou, Kehan Wang, Jie Xu, Dapeng Wu

Research output: Contribution to journalArticle

Abstract

The explosive growth of multimedia contents (MCs) in nowadays' mobile social networks pushes the edge computing facing severe security and online big data processing problems. On the one hand, the edge nodes (ENs) should help mobile users (MUs) find, cache and share MCs in the present of ever-increasing scale of multimedia big data. On the other hand, how to provide secure MC retrieval schemes to exclude dishonest-and-malicious untrusted ENs and to prevent privacy breaches from honest-but-curious ENs and MUs is a challenging issue. To tackle the above problems, this paper studies the privacy-preserving and trustworthy MCs retrieval system (MCRS) to make personalized MC recommendations from ENs to MUs with big data support. In our framework, each EN is modeled as a distributed context-aware online learner. ENs collaborate to learn MUs' preferences based on their contexts and previous behaviors and social intimacy. To support big data analytics, we establish an MC-cluster tree from top to the bottom to handle the dynamically varying cached MC datasets. A differentially private algorithm is proposed to preserve the data privacy among honest-but-curious ENs and MUs. To guarantee the trustworthy edge computing, a trust evaluation mechanism is designed to evaluate the reliability of ENs. We further consider the structure of edge networks to improve the performance of our algorithm. Experimental results validate that our new framework can support increasing multimedia big datasets while striking a balance among privacy-preserving level (PPL), Trustworthy level (TSL) and caching MC prediction accuracy.

Original languageEnglish (US)
JournalIEEE Transactions on Multimedia
DOIs
StateAccepted/In press - Jan 1 2018

Fingerprint

Data privacy
Big data

Keywords

  • big data
  • differential privacy
  • edge computing
  • online learning
  • social mutlimedia
  • trustworthiness

ASJC Scopus subject areas

  • Signal Processing
  • Media Technology
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Differentially-Private and Trustworthy Online Social Multimedia Big Data Retrieval in Edge Computing. / Zhou, Pan; Wang, Kehan; Xu, Jie; Wu, Dapeng.

In: IEEE Transactions on Multimedia, 01.01.2018.

Research output: Contribution to journalArticle

@article{8b9154d775964bd5a3844637d371760e,
title = "Differentially-Private and Trustworthy Online Social Multimedia Big Data Retrieval in Edge Computing",
abstract = "The explosive growth of multimedia contents (MCs) in nowadays' mobile social networks pushes the edge computing facing severe security and online big data processing problems. On the one hand, the edge nodes (ENs) should help mobile users (MUs) find, cache and share MCs in the present of ever-increasing scale of multimedia big data. On the other hand, how to provide secure MC retrieval schemes to exclude dishonest-and-malicious untrusted ENs and to prevent privacy breaches from honest-but-curious ENs and MUs is a challenging issue. To tackle the above problems, this paper studies the privacy-preserving and trustworthy MCs retrieval system (MCRS) to make personalized MC recommendations from ENs to MUs with big data support. In our framework, each EN is modeled as a distributed context-aware online learner. ENs collaborate to learn MUs' preferences based on their contexts and previous behaviors and social intimacy. To support big data analytics, we establish an MC-cluster tree from top to the bottom to handle the dynamically varying cached MC datasets. A differentially private algorithm is proposed to preserve the data privacy among honest-but-curious ENs and MUs. To guarantee the trustworthy edge computing, a trust evaluation mechanism is designed to evaluate the reliability of ENs. We further consider the structure of edge networks to improve the performance of our algorithm. Experimental results validate that our new framework can support increasing multimedia big datasets while striking a balance among privacy-preserving level (PPL), Trustworthy level (TSL) and caching MC prediction accuracy.",
keywords = "big data, differential privacy, edge computing, online learning, social mutlimedia, trustworthiness",
author = "Pan Zhou and Kehan Wang and Jie Xu and Dapeng Wu",
year = "2018",
month = "1",
day = "1",
doi = "10.1109/TMM.2018.2885509",
language = "English (US)",
journal = "IEEE Transactions on Multimedia",
issn = "1520-9210",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Differentially-Private and Trustworthy Online Social Multimedia Big Data Retrieval in Edge Computing

AU - Zhou, Pan

AU - Wang, Kehan

AU - Xu, Jie

AU - Wu, Dapeng

PY - 2018/1/1

Y1 - 2018/1/1

N2 - The explosive growth of multimedia contents (MCs) in nowadays' mobile social networks pushes the edge computing facing severe security and online big data processing problems. On the one hand, the edge nodes (ENs) should help mobile users (MUs) find, cache and share MCs in the present of ever-increasing scale of multimedia big data. On the other hand, how to provide secure MC retrieval schemes to exclude dishonest-and-malicious untrusted ENs and to prevent privacy breaches from honest-but-curious ENs and MUs is a challenging issue. To tackle the above problems, this paper studies the privacy-preserving and trustworthy MCs retrieval system (MCRS) to make personalized MC recommendations from ENs to MUs with big data support. In our framework, each EN is modeled as a distributed context-aware online learner. ENs collaborate to learn MUs' preferences based on their contexts and previous behaviors and social intimacy. To support big data analytics, we establish an MC-cluster tree from top to the bottom to handle the dynamically varying cached MC datasets. A differentially private algorithm is proposed to preserve the data privacy among honest-but-curious ENs and MUs. To guarantee the trustworthy edge computing, a trust evaluation mechanism is designed to evaluate the reliability of ENs. We further consider the structure of edge networks to improve the performance of our algorithm. Experimental results validate that our new framework can support increasing multimedia big datasets while striking a balance among privacy-preserving level (PPL), Trustworthy level (TSL) and caching MC prediction accuracy.

AB - The explosive growth of multimedia contents (MCs) in nowadays' mobile social networks pushes the edge computing facing severe security and online big data processing problems. On the one hand, the edge nodes (ENs) should help mobile users (MUs) find, cache and share MCs in the present of ever-increasing scale of multimedia big data. On the other hand, how to provide secure MC retrieval schemes to exclude dishonest-and-malicious untrusted ENs and to prevent privacy breaches from honest-but-curious ENs and MUs is a challenging issue. To tackle the above problems, this paper studies the privacy-preserving and trustworthy MCs retrieval system (MCRS) to make personalized MC recommendations from ENs to MUs with big data support. In our framework, each EN is modeled as a distributed context-aware online learner. ENs collaborate to learn MUs' preferences based on their contexts and previous behaviors and social intimacy. To support big data analytics, we establish an MC-cluster tree from top to the bottom to handle the dynamically varying cached MC datasets. A differentially private algorithm is proposed to preserve the data privacy among honest-but-curious ENs and MUs. To guarantee the trustworthy edge computing, a trust evaluation mechanism is designed to evaluate the reliability of ENs. We further consider the structure of edge networks to improve the performance of our algorithm. Experimental results validate that our new framework can support increasing multimedia big datasets while striking a balance among privacy-preserving level (PPL), Trustworthy level (TSL) and caching MC prediction accuracy.

KW - big data

KW - differential privacy

KW - edge computing

KW - online learning

KW - social mutlimedia

KW - trustworthiness

UR - http://www.scopus.com/inward/record.url?scp=85058151438&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85058151438&partnerID=8YFLogxK

U2 - 10.1109/TMM.2018.2885509

DO - 10.1109/TMM.2018.2885509

M3 - Article

JO - IEEE Transactions on Multimedia

JF - IEEE Transactions on Multimedia

SN - 1520-9210

ER -