Enhancing Wi-Fi Device Authentication Protocol Leveraging Channel State Information

Chen, Bing; Song, Yubo; Wu, Tianqi; Zheng, Tianyu; Chen, Hong‐Yuan; Wang, Junbo; Li, Tao

doi:10.1007/978-3-030-89814-4_3

Cited by 15 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Frigerio [8] proposed a DPGAN framework that utilizes differential privacy techniques to make GAN-based attacks inefficient. Both works by Hao [9] and Truex [10] combine secure multiparty computation and differential privacy to achieve a secure federated learning model. Triastcyn [11] proposes defense techniques for generating fake data at client nodes with minor modifications to allow data sharing instead of model sharing.…”

Section: Introductionmentioning

confidence: 99%

Privacy preservation for federated learning based on Gaussian noise scrambling

Cong¹,

Lei²,

Wang³

et al. 2023

Sixth International Conference on Advanced Electronic Materials, Computers, and Software Engineering (AEMCSE 2023)

View full text Add to dashboard Cite

This article discusses a privacy preservation for federated learning based on gaussian noise scrambling. The main objective of this model is to protect user data privacy and security by aggregating model parameters from multiple parties instead of raw data sets. However, attackers may still obtain sensitive information from the model parameter information transmitted during federated learning training through certain means. To address this issue, we propose a differential privacy noise addition scheme for federated learning. By adding noise to transmitted model parameters to some extent, it prevents attackers from inferring participant information through reverse inference. We also study Gaussian noise mechanism in differential privacy protection and prove it by combining characteristics of federated learning and blockchain technology for adding Gaussian noise size according to differential privacy requirements. This article tests their proposed differential privacy protection mechanism using the NSL-KDD dataset and finds that after adding differential privacy protection, models still have good anomaly recognition performance. This study contributes to the field of federated learning by proposing a novel approach for protecting user data privacy and security during training. The proposed approach can be used in various applications such as healthcare, finance, and social media where data privacy is crucial.

show abstract

Section: Introductionmentioning

confidence: 99%

Privacy preservation for federated learning based on Gaussian noise scrambling

Cong¹,

Lei²,

Wang³

et al. 2023

Sixth International Conference on Advanced Electronic Materials, Computers, and Software Engineering (AEMCSE 2023)

View full text Add to dashboard Cite

show abstract

“…Using federated learning technology, this model enables different participants to train models together without sharing their datasets, thus solving the problem of data islands. Participants can train the same model using their own data without sharing it with others to prevent privacy leaks [9] . Based on this foundation, in this model, parameter aggregation is not performed at the central server but at each participant's local device [10] .…”

Section: Introductionmentioning

confidence: 99%

Decentralized federated learning privacy protection aggregation

Cong¹,

Lei²,

Wang³

et al. 2023

Sixth International Conference on Advanced Electronic Materials, Computers, and Software Engineering (AEMCSE 2023)

View full text Add to dashboard Cite

The basic idea of federated learning is to aggregate the local model parameters of all participants to obtain a global model, which is more universal and has better performance. However, existing federated learning has the problem of a unique model, where all participants train their local models based on the same global model. However, in different real-world scenarios, data often has different features and distributions, and there is no universal model suitable for learning data from multiple scenarios. Therefore, existing federated learning technologies cannot achieve optimal performance in multiple scenarios. To solve this problem, this paper proposes a decentralized federated learning model where each participant independently selects other models similar to their local models and aggregates them to obtain a specialized model applicable to the local scenario. The model aggregates the parameters based on their similarity with the local model. Models with higher similarity will have a greater weight in the aggregation process. The parameter aggregation is not performed at the central server but at each participant's local device. Through this mechanism, the proposed model achieves specialization of local models for participants and improves performance in different scenarios.

show abstract

“…At present, with the deepening of artificial intelligence, machine learning and graph theory, more and more researchers are trying to explore potential vulnerabilities through new technologies or methods [7], such as functional code similarity detection, vulnerability detection based on deep learning, and using code knowledge graph to locate vulnerabilities [8]. These new ideas and methods provide a direction for solving the problem of vulnerability mining technology, and make vulnerability mining technology more automatic and intelligent [9].…”

Section: Introductionmentioning

confidence: 99%

Intelligent Association of CVE Vulnerabilities Based on Chain Reasoning

Sun,

Wang

2023

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

Vulnerability database data sources use semi-structured and unstructured data expression, which can provide convenience for researchers in vulnerability analysis and systematic study of vulnerability mechanism and vulnerability content. However, the traditional vulnerability database has some problems, such as weak correlation attribute, redundant data format and low visualization degree, which are difficult to be understood and analysed by machines. This paper proposes a CVE vulnerability intelligent association based on chain reasoning. By analysing the vulnerability description and the relationship between different vulnerability databases, investigating the software and systems affected by each vulnerability, linking relevant knowledge, inferring the hidden relationship of each vulnerability, building the relationship between the entity nodes of the vulnerability knowledge graph, and finally importing the data into the neo4j diagram database to build the vulnerability knowledge graph. By calculating the number of software associated with vulnerabilities, the CWE chain relationship is deduced, and the vulnerability knowledge graph constructed is used to conduct preliminary inference on the vulnerability scanning results, so as to obtain the hidden relationship between vulnerabilities and optimize the vulnerability scanning results.

show abstract

Enhancing Wi-Fi Device Authentication Protocol Leveraging Channel State Information

Cited by 15 publications

References 14 publications

Privacy preservation for federated learning based on Gaussian noise scrambling

Privacy preservation for federated learning based on Gaussian noise scrambling

Decentralized federated learning privacy protection aggregation

Intelligent Association of CVE Vulnerabilities Based on Chain Reasoning

Contact Info

Product

Resources

About