A trusted recommendation scheme for privacy protection based on federated learning

Wang, Yichuan; Tian, Yuying; Yin, Xinyue; Hei, Xinhong

doi:10.1007/s42045-020-00045-8

Cited by 25 publications

(11 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The training process occurs on the individual vehicles, ensuring that sensitive information remains on the device and is not exposed to external parties. This decentralized approach enhances data privacy and addresses concerns about sharing personal driving data [21][22]. Once the local training is complete, the updated model parameters are securely aggregated without revealing the specific data from each vehicle.…”

Section: Federated Learning In Safety Systemsmentioning

confidence: 99%

Federated Learning-Based Detection and Control Mechanism of In-Car Navigation Safety System

Gao,

Zhang,

2024

J Multimed Inf Syst

View full text Add to dashboard Cite

In-car navigation systems face challenges in ensuring safety while preserving data privacy. This paper proposes PrivNav, a federated learning scheme integrating differential privacy and secure multi-party computation for privacy-preserving learning. PrivNav enables vehicles to collaboratively train a model by aggregating locally computed updates without sharing raw data. Perturbations and secret sharing protect sensitive information and prevent inference attacks. PrivNav outperforms existing federated learning schemes by accommodating user dropouts, supporting customizable aggregation methods beyond FedAvg, and extending to decentralized scenarios without a trusted authority. Experiments demonstrate PrivNav's strong privacy guarantees and high accuracy, significantly enhancing the detection and control capabilities of in-car navigation safety systems. Precise event detection, abnormal situation differentiation, and reduced false alarms are achieved, improving overall system safety, trust, and performance.

show abstract

Section: Federated Learning In Safety Systemsmentioning

confidence: 99%

Federated Learning-Based Detection and Control Mechanism of In-Car Navigation Safety System

Gao,

Zhang,

2024

J Multimed Inf Syst

View full text Add to dashboard Cite

show abstract

“…The training process occurs on the individual vehicles, ensuring that sensitive information remains on the device and is not exposed to external parties. This decentralized approach enhances data privacy and addresses concerns about sharing personal driving data [21,22]. Once the local training is complete, the updated model parameters are securely aggregated without revealing the speci c data from each vehicle.…”

Section: Federated Learning In Safety Systemsmentioning

confidence: 99%

Federated learning-based detection and control mechanism of in-car navigation safety system

Gao

Zhang

2023

Preprint

View full text Add to dashboard Cite

The advancement of in-car navigation systems has dramatically improved driving experiences. However, ensuring the safety of these systems remains a critical concern. Federated learning provides a new solution for cooperative learning between non-mutually trusted entities. Through the mode of local training and central aggregation, the local data privacy of each entity is protected while training the global model. To achieve this, a federated learning method for deep learning that preserves privacy is developed by integrating differential privacy with secure multi-party computing. In this scheme, vehicles add perturbations to the local models obtained by local training and secretly share them with multiple central servers. The scheme protects the local information uploaded by users from being stolen and prevents the adversary from malicious inference from globally shared information such as the aggregation model. Additionally, the scheme enables users dropping out and implements a variety of aggregating methods. The aforementioned system may also easily be expanded to decentralized scenarios for real-world applications devoid of a trustworthy center. The experimental findings show that, in order to protect sensitive data obtained from in-car navigation systems during learning, the suggested strategy heavily emphasizes privacy protection. Simultaneously, the high accuracy achieved through the proposed federated learning scheme significantly enhances in-car navigation safety systems' detection and control capabilities. It enables precise and reliable event detection, differentiation of abnormal situations, and reduces false alarms, improving overall safety, user trust, and system performance.

show abstract

“…In the process of model learning, this paper continuously optimizes the loss function through optimization algorithms [8]. In order to find the optimal model parameters, the value of the loss function is minimized, and the training process of the neural network is regarded as an optimization problem.…”

Section: Adaptive Federated Deepmentioning

confidence: 99%

Predictive Analysis and Simulation of College Sports Performance Fused with Adaptive Federated Deep Learning Algorithm

Sun

2022

Journal of Sensors

View full text Add to dashboard Cite

With the widespread use of intelligent teaching, data containing student performance information continues to emerge, and artificial intelligence technology based on big data has made a qualitative leap. At present, the prediction of college students’ sports performance is only based on the past performance, and it does not reflect the student’s training effect very well. In order to solve these problems, this paper puts forward the analysis and simulation of college sports performance fusion with adaptive federated deep learning algorithm, aiming to study the influencing factors of student sports performance and suggestions for improvement. This paper uses an adaptive federated learning method and a personalized federated learning algorithm based on deep learning and then proposes a student performance prediction method. These methods integrate the quantitative methods of motor skill assessment and establish standards for college students, which are good standards for evaluating college students’ sports skills. This paper adopts the performance prediction framework and then establishes the sports performance prediction model. Through the analysis of sports performance analysis examples, it is concluded that the model proposed in this paper can accurately predict the student’s sports performance, and the average accuracy rate of each sports item has reached 91.7%.

show abstract

A trusted recommendation scheme for privacy protection based on federated learning

Cited by 25 publications

References 14 publications

Federated Learning-Based Detection and Control Mechanism of In-Car Navigation Safety System

Federated Learning-Based Detection and Control Mechanism of In-Car Navigation Safety System

Federated learning-based detection and control mechanism of in-car navigation safety system

Predictive Analysis and Simulation of College Sports Performance Fused with Adaptive Federated Deep Learning Algorithm

Contact Info

Product

Resources

About