4.7 Article

ATLAS: GAN-Based Differentially Private Multi-Party Data Sharing

Related references

Note: Only part of the references are listed.
Article Computer Science, Artificial Intelligence

Multi-Party Sequential Data Publishing Under Differential Privacy

Peng Tang et al.

Summary: This paper studies the problem of publishing a synthetic dataset that preserves approximate sequentiality information of the integrated dataset while satisfying differential privacy for each local dataset. The authors propose a distributed prediction suffix tree construction solution (DPST) that introduces a novel node splitting decision method and a batch-based tree construction approach to improve efficiency and reduce computation and communication costs.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2023)

Article Computer Science, Information Systems

Differentially private generative decomposed adversarial network for vertically partitioned data sharing

Zhenya Wang et al.

Summary: This paper proposes a differentially private generative decomposed adversarial network (DPGDAN) approach for vertically partitioned data sharing. DPGDAN decomposes the discriminator in the initial generative adversarial network (GAN) into several local discriminators and two relational discriminators. By combining the sanitized feedback from the local discriminators and outputs of the relational discriminators, the shared dataset can be approximated without compromising privacy. The effectiveness of DPGDAN is validated through extensive experiments.

INFORMATION SCIENCES (2023)

Proceedings Paper Computer Science, Information Systems

A Self-supervised Riemannian GNN with Time Varying Curvature for Temporal Graph Learning

Li Sun et al.

Summary: Representation learning on temporal graphs is of fundamental importance in various real-world applications. However, existing methods for obtaining time-dependent representations still face challenges, such as restricting the embedding space with a certain curvature and requiring abundant labels. In this paper, a novel self-supervised Riemannian graph neural network (SelfRGNN) is proposed to address these challenges, supporting time-varying curvature and enabling self-supervised learning through reweighting self-contrastive approaches and edge-based self-supervised curvature learning.

PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, CIKM 2022 (2022)

Proceedings Paper Computer Science, Information Systems

Collecting Individual Trajectories under Local Differential Privacy

Jianyu Yang et al.

Summary: This paper proposed a novel approach, PrivTC, to protect privacy and collect individual trajectories through locally differentially private grid construction and spectral learning, which was demonstrated to be effective through extensive experiments on real datasets.

2022 23RD IEEE INTERNATIONAL CONFERENCE ON MOBILE DATA MANAGEMENT (MDM 2022) (2022)

Article Computer Science, Theory & Methods

Fairness and Cost Constrained Privacy-Aware Record Linkage

Nan Wu et al.

Summary: Record linkage algorithms are developed to match and link records from different databases that refer to the same real-world entity based on identifiers like name, address, age, and gender, with privacy constraints. Differential privacy combined with computationally efficient encoding methods like Bloom filter encoding has been used in developing PPRL for better performance.

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY (2022)

Article Computer Science, Information Systems

DI-Mondrian: Distributed improved Mondrian for satisfaction of the L-diversity privacy model using Apache Spark

Farough Ashkouti et al.

Summary: This paper presents an improved Mondrian multidimensional anonymization method within the Apache Spark framework, focusing on reducing information loss and improving classifier performance through dynamic selection of cutting points and criteria. Experimental results demonstrate the advantages of this method in large-scale data anonymization.

INFORMATION SCIENCES (2021)

Article Computer Science, Information Systems

An optimal (ε, δ)-differentially private learning of distributed deep fuzzy models

Mohit Kumar et al.

Summary: This study introduces a privacy-preserving framework for distributed deep fuzzy learning under the differential privacy framework. By learning local deep fuzzy models through variational Bayesian inference, noise magnitude can be reduced to increase utility, leveraging the robustness feature of rule-based fuzzy systems. The proposed architecture separates private local training data from globally shared data using a privacy wall, utilizing noise adding mechanisms to achieve differential privacy and prevent adversaries from accessing the training data directly.

INFORMATION SCIENCES (2021)

Article Computer Science, Information Systems

A privacy-preserving public integrity check scheme for outsourced EHRs

Yuan Su et al.

Summary: This paper proposes an efficient integrity check scheme for classified EHRs, which protects the privacy of EHRs and improves efficiency by combining classified storage with special data structures, implementing batch auditing of EHRs across multiple categories.

INFORMATION SCIENCES (2021)

Article Computer Science, Hardware & Architecture

Differentially Private Publication of Vertically Partitioned Data

Peng Tang et al.

Summary: This paper focuses on the issue of publishing vertically partitioned data under differential privacy, proposing a differentially private latent tree (DPLT) approach that can generate synthetic datasets while protecting data privacy. Through extensive experiments, it is demonstrated that this method offers desirable data utility with low computation costs.

IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING (2021)

Article Computer Science, Artificial Intelligence

Clustered Federated Learning: Model-Agnostic Distributed Multitask Optimization Under Privacy Constraints

Felix Sattler et al.

Summary: Federated learning is widely used for collaborative training of machine learning models under privacy constraints, but can yield suboptimal results when local data distributions diverge. Clustered FL is a novel framework that addresses this issue by grouping clients with jointly trainable data distributions based on geometric properties of the FL loss surface.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2021)

Proceedings Paper Computer Science, Information Systems

PRISM: Private Verifiable Set Computation over Multi-Owner Outsourced Databases

Yin Li et al.

Summary: PRISM is a secret sharing based approach that enables efficient computation of private set operations and supports result verification techniques to detect malicious adversaries without requiring communication among servers. Experimental results show its scalability in terms of the number of data owners and database sizes.

SIGMOD '21: PROCEEDINGS OF THE 2021 INTERNATIONAL CONFERENCE ON MANAGEMENT OF DATA (2021)

Proceedings Paper Computer Science, Artificial Intelligence

Towards Fair Federated Learning with Zero-Shot Data Augmentation

Weituo Hao et al.

Summary: This work presents a federated learning scheme that improves fairness by using zero-shot data augmentation to mitigate statistical heterogeneity and encourage more uniform accuracy performance across clients in federated networks.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021 (2021)

Article Computer Science, Information Systems

Survey on Improving Data Utility in Differentially Private Sequential Data Publishing

Xinyu Yang et al.

Summary: This paper comprehensively reviews and investigates existing schemes for providing differential privacy from a broad perspective, discussing issues such as privacy guarantees, effectiveness, and efficiency in improving data utility. The existing schemes are categorized into different mechanisms, with a focus on analyzing and comparing their concepts and principles, aiming to enhance data utility.

IEEE TRANSACTIONS ON BIG DATA (2021)

Article Computer Science, Information Systems

Game Theory Based Correlated Privacy Preserving Analysis in Big Data

Xiaotong Wu et al.

Summary: Privacy preservation in big data is a critical issue, with differential privacy mechanism vulnerable when multiple datasets are correlated. This leads to a shift from a trade-off between privacy and utility to a game problem. The paper introduces the concept of correlated differential privacy and analyzes the existence and uniqueness of pure Nash Equilibrium in a game model of multiple players publishing data sanitized by differential privacy.

IEEE TRANSACTIONS ON BIG DATA (2021)

Article Computer Science, Artificial Intelligence

Enhanced Privacy Preserving Group Nearest Neighbor Search

Yuncheng Wu et al.

Summary: The paper presents four protection objectives in privacy preserving kGNN search and designs two privacy preserving solutions, which reduce communication cost and user computational cost while protecting user privacy.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2021)

Article Computer Science, Artificial Intelligence

Multi-Party High-Dimensional Data Publishing Under Differential Privacy

Xiang Cheng et al.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2020)

Article Computer Science, Information Systems

Differentially private distributed optimization for multi-agent systems via the augmented Lagrangian algorithm

Yuan-Wei Lv et al.

INFORMATION SCIENCES (2020)

Article Computer Science, Information Systems

Differentially private publication of streaming trajectory data

Xiaofeng Ding et al.

INFORMATION SCIENCES (2020)

Article Computer Science, Theory & Methods

SAQE

Johes Bater et al.

Proceedings of the VLDB Endowment (2020)

Article Computer Science, Information Systems

Private Empirical Risk Minimization With Analytic Gaussian Mechanism for Healthcare System

Jiahao Ding et al.

IEEE TRANSACTIONS ON BIG DATA (2020)

Article Computer Science, Information Systems

Answering Multi-Dimensional Range Queries under Local Differential Privacy

Jianyu Yang et al.

PROCEEDINGS OF THE VLDB ENDOWMENT (2020)

Article Computer Science, Hardware & Architecture

Efficient and Private Scoring of Decision Trees, Support Vector Machines and Logistic Regression Models Based on Pre-Computation

Martine De Cock et al.

IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING (2019)

Article Computer Science, Artificial Intelligence

Federated Machine Learning: Concept and Applications

Qiang Yang et al.

ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY (2019)

Article Computer Science, Theory & Methods

GANobfuscator: Mitigating Information Leakage Under GAN via Differential Privacy

Chugui Xu et al.

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY (2019)

Article Computer Science, Artificial Intelligence

Precise and Fast Cryptanalysis for Bloom Filter Based Privacy-Preserving Record Linkage

Peter Christen et al.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2019)

Article Computer Science, Information Systems

Locally differentially private item-based collaborative filtering

Taolin Guo et al.

INFORMATION SCIENCES (2019)

Article Computer Science, Information Systems

The optimal upper bound of the number of queries for Laplace mechanism under differential privacy

Xiaoguang Li et al.

INFORMATION SCIENCES (2019)

Article Computer Science, Information Systems

PrivateSQL: A Differentially Private SQL Query Engine

Ios Kotsogiannis et al.

PROCEEDINGS OF THE VLDB ENDOWMENT (2019)

Article Computer Science, Information Systems

Secure Multi-Party Functional Dependency Discovery

Chang Ge et al.

PROCEEDINGS OF THE VLDB ENDOWMENT (2019)

Proceedings Paper Computer Science, Artificial Intelligence

Privacy-Preserving Temporal Record Linkage

Thilina Ranbaduge et al.

2018 IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM) (2018)

Proceedings Paper Computer Science, Information Systems

Privacy at Scale: Local Differential Privacy in Practice

Graham Cormode et al.

SIGMOD'18: PROCEEDINGS OF THE 2018 INTERNATIONAL CONFERENCE ON MANAGEMENT OF DATA (2018)

Article Computer Science, Information Systems

Shrinkwrap: Efficient SQL Query Processing in Differentially Private Data Federations

Johes Bater et al.

PROCEEDINGS OF THE VLDB ENDOWMENT (2018)

Proceedings Paper Computer Science, Information Systems

Composing Differential Privacy and Secure Computation: A case study on scaling private record linkage

Xi He et al.

CCS'17: PROCEEDINGS OF THE 2017 ACM SIGSAC CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY (2017)

Article Computer Science, Information Systems

SMCQL: Secure Querying for Federated Databases

Johes Bater et al.

PROCEEDINGS OF THE VLDB ENDOWMENT (2017)

Proceedings Paper Computer Science, Information Systems

Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning

Briland Hitaj et al.

CCS'17: PROCEEDINGS OF THE 2017 ACM SIGSAC CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY (2017)

Article Computer Science, Hardware & Architecture

Collaborative Search Log Sanitization: Toward Differential Privacy and Boosted Utility

Yuan Hong et al.

IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING (2015)

Proceedings Paper Computer Science, Artificial Intelligence

Differentially Private High-Dimensional Data Publication via Sampling-Based Inference

Rui Chen et al.

KDD'15: PROCEEDINGS OF THE 21ST ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING (2015)

Article Computer Science, Hardware & Architecture

Secure Two-Party Differentially Private Data Release for Vertically Partitioned Data

Noman Mohammed et al.

IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING (2014)

Proceedings Paper Computer Science, Theory & Methods

RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response

Ulfar Erlingsson et al.

CCS'14: PROCEEDINGS OF THE 21ST ACM CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY (2014)

Article Computer Science, Theory & Methods

The Algorithmic Foundations of Differential Privacy

Cynthia Dwork et al.

FOUNDATIONS AND TRENDS IN THEORETICAL COMPUTER SCIENCE (2013)

Article Computer Science, Artificial Intelligence

k-anonymity:: A model for protecting privacy

L Sweeney

INTERNATIONAL JOURNAL OF UNCERTAINTY FUZZINESS AND KNOWLEDGE-BASED SYSTEMS (2002)