Concentrated Differentially Private Federated Learning With Performance Analysis

Hu, Rui; Guo, Yuanxiong

doi:10.1109/ojcs.2021.3099108

Cited by 22 publications

(8 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A vehicle will be connected to an RSU as it enters the area of that RSU, and then the data would be transmitted to MECs. The DPFL-F2IDS is defined by FedAvg ( 14 ) and a related problem definition for data sharing in IoV scenarios ( 22 ). Vehicles V = { V 1 , V 2 , . . . , V K } are designated as clients in federated learning while the MEC U = { u 1 , u 2 , . . . , u m } servers are regarded as servers.…”

Section: Preliminaries Of Methods and Problem Definitionmentioning

confidence: 99%

“…Wei et al ( 21 ) also proposed that artificial noise can be added to parameters on the client side before aggregating. Hu et al ( 22 ) suggested a DPFL scheme with periodic averaging and device sampling by integrating FedAvg and a kind of local differential privacy named zero-concentration DP (zCDP). Lu et al ( 23 ) established a problem definition of resource sharing by DPFL in inter-vehicular networks.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Secure Intrusion Detection by Differentially Private Federated Learning for Inter-Vehicle Networks

Zhang

et al. 2023

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

Along with providing several benefits, the unprecedented growth of connected and automated vehicles brings worries about damaging cyber attacks. Network-based intrusion detection systems (IDSs) using deep learning methods can effectively mitigate the threats by promptly detecting malicious behaviors. However, the centralized learning mode may cause data leverage. Federated learning has emerged as a new distributed machine learning training paradigm to preserve data privacy by allowing clients to train and validate models locally with their data and then send the model parameters to the central server. First, we propose a new framework named DPFL-F2IDS scheme for an edge inter-vehicle network that transmits Basic Safety Messages, which consists of Differentially Private Federated Learning (DPFL) and F2IDS (Framework for IDS). DPFL can defend against the member inference attacks faced by the standard federated learning, but difficulties still exist in making a tradeoff on the utility metrics and privacy metrics. Second, experiments by centralized learning methods were performed on the VeReMi Extension dataset. Third, the performance of federated learning by different numbers of vehicles and different optimizers is evaluated. DPFL by different noise values is also evaluated. Results clarified that the F1-scores reached 0.9915 and 0.9700 by long short-term memory (LSTM)-based intrusion detection for binary classification and multi-classification in the centralized learning mode, respectively. The utility results achieved by federated averaging (FedAvg) with Adabound optimizer were closer to the centralized learning mode than the classical FedAvg algorithms. The optimal values of the noise multipliers were also found without degrading the model quality and preserving privacy.

show abstract

Section: Preliminaries Of Methods and Problem Definitionmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Secure Intrusion Detection by Differentially Private Federated Learning for Inter-Vehicle Networks

Zhang

et al. 2023

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

show abstract

“…GDP [28][29][30][31][32][33][34][35][36][37] LDP 32,[38][39][40][41][42][43][44][45][46][47][48][49][50][51][52] Hybrid-DP [53][54][55][56][57][58][59][60][61][62][63][64][65][66][67] • Homomorphic encryption 56, • Trusted execution environment [94][95][96][97][98][99][100][101][102][103]…”

Section: Attack Attack Target Defense Defense Targetmentioning

confidence: 99%

Privacy preserving and secure robust federated learning: A survey

Han,

Lu,

Wang

et al. 2024

Concurrency and Computation

View full text Add to dashboard Cite

SummaryFederated learning (FL) has emerged as a promising solution to address the challenges posed by data silos and the need for global data fusion. It offers a distributed machine learning framework with privacy‐preserving features, allowing model training without the need to collect user data. However, FL also presents significant security and privacy threats that hinder its widespread adoption. The requirements of privacy and security in FL are inherently conflicting. Privacy necessitates the concealment of individual client updates, while security requires the disclosure of client updates to detect anomalies. While most existing research focused on the privacy and security aspects of FL, very few studies have addressed the compatibility of these two demands. In this work, we aim to bridge this gap by proposing a comprehensive defense scheme that ensures privacy, security, and compatibility in FL. We categorize the existing literature into two key directions: privacy defense and security defense. Privacy defense includes methods based on additive masks, differential privacy, homomorphic encryption, and trusted execution environment, whereas security defense encompasses distance‐, performance‐, clustering‐, and similarity‐based anomaly detection techniques and statistical information‐based anomaly update bypassing techniques when the server is trusted and privacy‐compatible anomaly update detection techniques when the server is not trusted. In addition, this article presents decentralized FL solutions based on blockchain. For each direction, we discuss specific technical solutions, their advantages, and disadvantages. By evaluating various defense methods, we identify the most suitable approach to address the primary challenge of “achieving a secure and robust FL system against malicious adversaries while protecting users' privacy.” We then propose a theoretical reference framework for end‐to‐end protection of privacy and security in FL for the key problem, which summarizes the attack surface of FL systems from the client to the server under the security model where the client and server are malicious. Leveraging the strengths and characteristics of existing schemes, our proposed framework integrates multiple techniques to strike a balance between privacy, usability, and efficiency. This framework serves as a valuable reference and provides insights for future work in the field. Finally, we also provide recommendations for future research directions in this field.

show abstract

“…In [189], the Skellam mechanism instead of the Gaussian mechanism is introduced and the authors explore its performance when combining it with central RDP, distributed RDP with secure encryption, respectively. The authors in [190] combine LDP with secure encryption and zCDP to achieve a good utility-privacy trade-off by adding less noise in every training iteration. It is necessary to consider the problem of trading off the information privacy between model utility.…”

Section: Dp-based Aggregationmentioning

confidence: 99%

Privacy-Preserving Aggregation in Federated Learning: A Survey

Liu¹,

Guo²,

Yang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Over the recent years, with the increasing adoption of Federated Learning (FL) algorithms and growing concerns over personal data privacy, Privacy-Preserving Federated Learning (PPFL) has attracted tremendous attention from both academia and industry. Practical PPFL typically allows multiple participants to individually train their machine learning models, which are then aggregated to construct a global model in a privacy-preserving manner. As such, Privacy-Preserving Aggregation (PPAgg) as the key protocol in PPFL has received substantial research interest. This survey aims to fill the gap between a large number of studies on PPFL, where PPAgg is adopted to provide a privacy guarantee, and the lack of a comprehensive survey on the PPAgg protocols applied in FL systems. In this survey, we review the PPAgg protocols proposed to address privacy and security issues in FL systems. The focus is placed on the construction of PPAgg protocols with an extensive analysis of the advantages and disadvantages of these selected PPAgg protocols and solutions. Additionally, we discuss the open-source FL frameworks that support PPAgg. Finally, we highlight important challenges and future research directions for applying PPAgg to FL systems and the combination of PPAgg with other technologies for further security improvement.

show abstract

Concentrated Differentially Private Federated Learning With Performance Analysis

Cited by 22 publications

References 26 publications

Secure Intrusion Detection by Differentially Private Federated Learning for Inter-Vehicle Networks

Secure Intrusion Detection by Differentially Private Federated Learning for Inter-Vehicle Networks

Privacy preserving and secure robust federated learning: A survey

Privacy-Preserving Aggregation in Federated Learning: A Survey

Contact Info

Product

Resources

About