Titlebook: Security and Privacy in Social Networks and Big Data; 8th International Sy Xiaofeng Chen,Xinyi Huang,Mirosław Kutyłowski Conference proceed

整体

留恋

过于平凡

1865-0929 2022, which took place in Xi‘an, China, in October 2022..The 23 papers presented in this volume were carefully reviewed and selected from 103 submissions. The papers were evaluated on the basis of their significance, novelty, technical quality, as well as on their practical impact or their level of

CRP743

D2D Authentication Scheme for IoT-enabled Smart Homee can ensure that two intelligent devices can authenticate each other with the assistance of a home gateway. The security and performance analysis shows that the proposal is secure and efficient for the application in the smart home environment.

的阐明

Secure Asynchronous Federated Learning for Edge Computing Deviceseighted secure asynchronous federated learning scheme, WASecAgg, which can ensure training accuracy and data privacy on the premise of guaranteeing the training efficiency of federated learning. The final experiments show that WASecAgg performs better in terms of training efficiency, training accuracy and privacy-preserving of federated learning.

crease

A Network Security Situation Assessment Method Based on Multi-attention Mechanism and HHO-ResNeXttraditional convolutional neural network. The experiments on a network security dataset show that the model is superior to other models in the network security situation assessment effect and its comprehensive performance in accuracy, precision and F-score.

Platelet

Detection and Defense Against DDoS Attack on SDN Controller Based on Feature Selection the attack detection module will detect the DDoS attack. Finally, attack defense module is introduced to filter attack packets and protect controller computing resources. We used the NSL-KDD dataset for evaluation and comparison with other schemes. Experimental results show that our scheme can detect and defend against DDoS attacks accurately.

废墟

精致

NEG

A Secure Word Vector Training Scheme Based on Inner-Product Functional Encryptionrom a large amount of datasets. Training word vector in machine learning needs a lot of datasets to train and output a model, however, some of which might contain private and sensitive information, and the training phase will lead to the exposure of the trained model and user datasets. In order to o