4.7 Article

Privacy and Efficiency of Communications in Federated Split Learning

Related references

Note: Only part of the references are listed.
Article Computer Science, Theory & Methods

Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges

Yoshitomo Matsubara et al.

Summary: Mobile devices increasingly rely on deep neural networks for complex inference tasks. Split computing (SC) and early exiting (EE) approaches have been proposed to reduce computational burden and energy consumption. This article provides a comprehensive survey of the state of the art in SC and EE strategies and presents a set of compelling research challenges.

ACM COMPUTING SURVEYS (2023)

Article Engineering, Civil

FedCPF: An Efficient-Communication Federated Learning Approach for Vehicular Edge Computing in 6G Communication Networks

Su Liu et al.

Summary: In this study, an efficient communication approach called FedCPF is proposed to achieve fast convergence and improve testing accuracy in vehicular edge computing. By customizing local training strategies, introducing partial client participation rules, and implementing flexible aggregation policies, FedCPF outperforms the traditional FedAVG algorithm and performs well in various FL settings.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2022)

Proceedings Paper Computer Science, Artificial Intelligence

ResSFL: A Resistance Transfer Framework for Defending Model Inversion Attack in Split Federated Learning

Jingtao Li et al.

Summary: The ResSFL framework is designed to resist Model Inversion attacks in Split Federated Learning by deriving a resistant feature extractor through attacker-aware training and initializing the client-side model with it before standard training. It successfully mitigates MI attacks on a VGG-11 model with high reconstruction Mean-Square-Error and achieves a balanced accuracy level on the CIFAR-100 dataset.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2022)

Article Engineering, Electrical & Electronic

Privacy-Preserving Federated Learning for UAV-Enabled Networks: Learning-Based Joint Scheduling and Resource Management

Helin Yang et al.

Summary: The paper presents an asynchronous federated learning framework for multi-UAV-enabled networks, which allows for distributed computing and enhances federated convergence speed and accuracy through device selection strategy and A3C-based algorithm.

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS (2021)

Article Chemistry, Analytical

BBNet: A Novel Convolutional Neural Network Structure in Edge-Cloud Collaborative Inference

Hongbo Zhou et al.

Summary: This paper proposes a novel convolutional neural network structure BBNet, which accelerates collaborative inference by channel pruning and feature map compression. Compared with the original network, BBNet achieves up to 5.67x and 11.57x compression rates in terms of FLOPs and parameters, respectively.

SENSORS (2021)

Proceedings Paper Computer Science, Hardware & Architecture

Federated or Split? A Performance and Privacy Analysis of Hybrid Split and Federated Learning Architectures

Valeria Turina et al.

Summary: The study analyzes the tradeoffs between traditional machine learning methods and distributed machine learning techniques, proposing a new hybrid Federated Split Learning architecture to combine the benefits of both efficiency and privacy.

2021 IEEE 14TH INTERNATIONAL CONFERENCE ON CLOUD COMPUTING (CLOUD 2021) (2021)

Article Engineering, Electrical & Electronic

Unified Biometric Privacy Preserving Three-Factor Authentication and Key Agreement for Cloud-Assisted Autonomous Vehicles

Qi Jiang et al.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2020)

Proceedings Paper Computer Science, Artificial Intelligence

NoPeek: Information leakage reduction to share activations in distributed deep learning

Praneeth Vepakomma et al.

20TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOPS (ICDMW 2020) (2020)

Proceedings Paper Computer Science, Information Systems

Privacy-Sensitive Parallel Split Learning

Joohyung Jeon et al.

2020 34TH INTERNATIONAL CONFERENCE ON INFORMATION NETWORKING (ICOIN 2020) (2020)

Article Computer Science, Information Systems

An Attack-Based Evaluation Method for Differentially Private Learning Against Model Inversion Attack

Cheolhee Park et al.

IEEE ACCESS (2019)

Article Computer Science, Hardware & Architecture

Distributed learning of deep neural network over multiple agents

Otkrist Gupta et al.

JOURNAL OF NETWORK AND COMPUTER APPLICATIONS (2018)

Proceedings Paper Computer Science, Information Systems

Learning from Differentially Private Neural Activations with Edge Computing

Yunlong Mao et al.

2018 THIRD IEEE/ACM SYMPOSIUM ON EDGE COMPUTING (SEC) (2018)

Proceedings Paper Computer Science, Software Engineering

Neurosurgeon: Collaborative Intelligence Between the Cloud and Mobile Edge

Yiping Kang et al.

OPERATING SYSTEMS REVIEW (2017)

Proceedings Paper Computer Science, Hardware & Architecture

Neurosurgeon: Collaborative Intelligence Between the Cloud and Mobile Edge

Yiping Kang et al.

TWENTY-SECOND INTERNATIONAL CONFERENCE ON ARCHITECTURAL SUPPORT FOR PROGRAMMING LANGUAGES AND OPERATING SYSTEMS (ASPLOS XXII) (2017)

Proceedings Paper Computer Science, Information Systems

Model Inversion Attacks for Prediction Systems: Without Knowledge of Non-Sensitive Attributes

Seira Hidano et al.

2017 15TH ANNUAL CONFERENCE ON PRIVACY, SECURITY AND TRUST (PST) (2017)

Proceedings Paper Computer Science, Information Systems

Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures

Matt Fredrikson et al.

CCS'15: PROCEEDINGS OF THE 22ND ACM SIGSAC CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY (2015)