4.8 Article

Cryptanalysis and Improvement of DeepPAR: Privacy-Preserving and Asynchronous Deep Learning for Industrial IoT

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Computer Science, Information Systems

PDLHR: Privacy-Preserving Deep Learning Model With Homomorphic Re-Encryption in Robot System

Yange Chen et al.

Summary: The article proposes a privacy-preserving deep learning model with homomorphic re-encryption and secure calculation tools for robot systems, addressing privacy leakage issues, improving efficiency, and preserving the privacy of input data, training model, and inference results.

IEEE SYSTEMS JOURNAL (2022)

Article Computer Science, Artificial Intelligence

Privacy-preserving image multi-classification deep learning model in robot system of industrial IoT

Yange Chen et al.

Summary: A novel privacy-preserving image multi-classification deep-learning (PIDL) model is presented in this paper, with two schemes proposed that adopt secure calculation protocols applied in a fog control center (FCC) with a non-colluding honest server to protect data and model privacy in robot systems. The proposed schemes realize security, correctness, and efficiency with low communication and computational costs, as demonstrated in security analysis and performance evaluation.

NEURAL COMPUTING & APPLICATIONS (2021)

Article Computer Science, Theory & Methods

Accurate Differentially Private Deep Learning on the Edge

Rui Han et al.

Summary: The study introduces PrivateDL to improve the accuracy of deep learning models while fulfilling privacy guarantees. PrivateDL features sampling-based sensitivity estimation for local noise calibration and the combination of large batch sizes and critical data identification in global training.

IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS (2021)

Proceedings Paper Computer Science, Artificial Intelligence

PFA: Privacy-preserving Federated Adaptation for Effective Model Personalization

Bingyan Liu et al.

Summary: This paper introduces a new concept called federated adaptation to achieve better personalization results by adjusting the trained model in a federated manner. The proposed PFA framework leverages the sparsity property of neural networks to generate privacy-preserving representations and efficiently identify clients with similar data distributions, ultimately outperforming other state-of-the-art methods while ensuring user privacy.

PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE 2021 (WWW 2021) (2021)

Article Automation & Control Systems

DeepPAR and DeepDPA: Privacy Preserving and Asynchronous Deep Learning for Industrial IoT

Xiaoyu Zhang et al.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2020)

Article Computer Science, Artificial Intelligence

Privacy-enhanced multi-party deep learning

Maoguo Gong et al.

NEURAL NETWORKS (2020)

Article Computer Science, Information Systems

PMC: A Privacy-preserving Deep Learning Model Customization Framework for Edge Computing

Bingyan Liu et al.

PROCEEDINGS OF THE ACM ON INTERACTIVE MOBILE WEARABLE AND UBIQUITOUS TECHNOLOGIES-IMWUT (2020)

Article Computer Science, Theory & Methods

Secure and Differentially Private Logistic Regression for Horizontally Distributed Data

Miran Kim et al.

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY (2020)

Article Computer Science, Information Systems

New publicly verifiable computation for batch matrix multiplication

Xiaoyu Zhang et al.

INFORMATION SCIENCES (2019)

Article Computer Science, Information Systems

Privacy-Preserving Distributed Deep Learning via Homomorphic Re-Encryption

Fengyi Tang et al.

ELECTRONICS (2019)

Proceedings Paper Computer Science, Hardware & Architecture

Differentially-Private Deep Learning from an Optimization Perspective

Liyao Xiang et al.

IEEE CONFERENCE ON COMPUTER COMMUNICATIONS (IEEE INFOCOM 2019) (2019)

Article Automation & Control Systems

Certificateless Public Key Authenticated Encryption With Keyword Search or Industrial Internet of Things

Debiao He et al.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2018)

Article Computer Science, Theory & Methods

Privacy-Preserving Deep Learning via Additively Homomorphic Encryption

Le Trieu Phong et al.

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY (2018)

Article Computer Science, Information Systems

Privacy preserving multi-party computation delegation for deep learning in cloud computing

Xu Ma et al.

INFORMATION SCIENCES (2018)

Article Computer Science, Theory & Methods

Dynamic Differential Privacy for ADMM-Based Distributed Classification Learning

Tao Zhang et al.

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY (2017)

Article Computer Science, Artificial Intelligence

Preserving differential privacy in convolutional deep belief networks

NhatHai Phan et al.

MACHINE LEARNING (2017)

Proceedings Paper Computer Science, Information Systems

Practical Secure Aggregation for Privacy-Preserving Machine Learning

Keith Bonawitz et al.

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

Article Automation & Control Systems

Internet of Things in Industries: A Survey

Li Da Xu et al.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2014)

Article Health Care Sciences & Services

Lightweight ECC Based RFID Authentication Integrated with an ID Verifier Transfer Protocol

Debiao He et al.

JOURNAL OF MEDICAL SYSTEMS (2014)

Review Green & Sustainable Science & Technology

Multi-operation management of a typical micro-grids using Particle Swarm Optimization: A comparative study

Amjad Anvari Moghaddam et al.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2012)

Article Computer Science, Artificial Intelligence

Privacy preserving Back-propagation neural network learning over arbitrarily partitioned data

Ankur Bansal et al.

NEURAL COMPUTING & APPLICATIONS (2011)