Privacy-Encoding Models for Preserving Utility of Machine Learning Algorithms in Social Media

Salim, Sara; Moustafa, Nour; Turnbull, Benjamin

doi:10.1109/trustcom50675.2020.00115

Cited by 3 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1,13 Constraint modification-based methods perturb the structure of the original graph with nodes or links addition/deletion while meeting certain constraints. 12,31,32 Random perturbation-based techniques randomly add/remove or switch nodes and links to preserve user privacy. 33 Random walk-based methods add noise to target links by random walk.…”

Section: Privacy-preserving Graph Publishing (Ppgp)mentioning

confidence: 99%

“…And the value K is set to 8, which is the same as the study. 32 Privacy Encoding (PE) 12 : PE is designed to defend against privacy inference attacks. For SN data, the model provides two levels of privacy protection.…”

Section: Baseline Modelsmentioning

confidence: 99%

“…Graph perturbation strategies can be classified into three types: constraint modification ‐based, random perturbation ‐based, and random walk ‐based 1,13 . Constraint modification ‐based methods perturb the structure of the original graph with nodes or links addition/deletion while meeting certain constraints 12,31,32 . Random perturbation ‐based techniques randomly add/remove or switch nodes and links to preserve user privacy 33 .…”

Section: Related Workmentioning

confidence: 99%

“…1,9,10 For instance, the study 11 uses the trust score of the available resources during classification learning to do privacy-preserving decisions for secure data sharing. Sara Salim et al 12 proposed a two-level hybrid privacy encoding model that perturbs and normalizes SN data over node attributes and links. The research 13 anonymizes private attributes in the graph embedding matrix to defend against attribute inference attacks.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Privacy‐preserving graph publishing with disentangled variational information bottleneck

Ma,

Li,

Sun

et al. 2023

Concurrency and Computation

View full text Add to dashboard Cite

SummarySocial networks collect enormous amounts of user personal and behavioral data, which could threaten users' privacy if published or shared directly. Privacy‐preserving graph publishing (PPGP) can make user data available while protecting private information. For this purpose, in PPGP, anonymization methods like perturbation and generalization are commonly used. However, traditional anonymization methods are challenging in balancing high‐level privacy and utility, ineffective at defending against both various link and hybrid inference attacks, as well as vulnerable to graph neural network (GNN)‐based attacks. To solve those problems, we present a novel privacy‐disentangled approach that disentangles private and non‐private information for a better privacy‐utility trade‐off. Moreover, we propose a unified graph deep learning framework for PPGP, denoted privacy‐disentangled variational information bottleneck (PDVIB). Using low‐dimensional perturbations, the model generates an anonymized graph to defend against various inference attacks, including GNN‐based attacks. Particularly, the model fits various privacy settings by employing adjustable perturbations at the node level. With three real‐world datasets, PDVIB is demonstrated to generate robust anonymous graphs that defend against various privacy inference attacks while maintaining the utility of non‐private information.

show abstract

Section: Privacy-preserving Graph Publishing (Ppgp)mentioning

confidence: 99%

Section: Baseline Modelsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Privacy‐preserving graph publishing with disentangled variational information bottleneck

Ma,

Li,

Sun

et al. 2023

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

A Blockchain-Enabled Explainable Federated Learning for Securing Internet-of-Things-Based Social Media 3.0 Networks

Salim¹,

Turnbull

Moustafa

2024

IEEE Trans. Comput. Soc. Syst.

View full text Add to dashboard Cite

Perturbation-enabled Deep Federated Learning for Preserving Internet of Things-based Social Networks

Salim¹,

Moustafa²,

Turnbull

et al. 2022

ACM Trans. Multimedia Comput. Commun. Appl.

View full text Add to dashboard Cite

Federated Learning (FL), as an emerging form of distributed machine learning, can protect participants’ private data from being substantially disclosed to cyber adversaries. It has potential uses in many large-scale, data-rich environments, such as the Internet of Things (IoT), Industrial IoT, Social Media, and the emerging SM 3.0. However, federated learning is susceptible to some forms of data leakage through model inversion attacks. Such attacks occur through the analysis of participants’ uploaded model updates. Model inversion attacks can reveal private data and potentially undermine some critical reasons for employing federated learning paradigms. This paper proposes novel differential privacy (DP)-based deep federated learning framework. We theoretically prove that our framework can fulfill DP’s requirements under distinct privacy levels by appropriately adjusting scaled variances of Gaussian noise. We then develop a Differentially Private Data-Level Perturbation (DP-DLP) mechanism to conceal any single data point’s impact on the training phase. Experiments on real-world datasets, specifically the social media 3.0, Iris, and Human Activity Recognition (HAR) datasets, demonstrate that the proposed mechanism can offer high privacy, enhanced utility, and elevated efficiency. Consequently, it simplifies the development of various DP-based FL models with different trade-off preferences on data utility and privacy levels.

show abstract

Privacy-Encoding Models for Preserving Utility of Machine Learning Algorithms in Social Media

Cited by 3 publications

References 13 publications

Privacy‐preserving graph publishing with disentangled variational information bottleneck

Privacy‐preserving graph publishing with disentangled variational information bottleneck

A Blockchain-Enabled Explainable Federated Learning for Securing Internet-of-Things-Based Social Media 3.0 Networks

Perturbation-enabled Deep Federated Learning for Preserving Internet of Things-based Social Networks

Contact Info

Product

Resources

About