TY - GEN
T1 - Machine Learning-Enabled Distributed Framework for Attack Detection in Social Networks
AU - Yotxay, Sangthong
AU - Azzaoui, Abir E.L.
AU - Park, Jong Hyuk
N1 - Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
PY - 2023
Y1 - 2023
N2 - With rapidly evolving technology, social networks are the most popular medium for communicating information from person to person on the Internet. Nowadays, people of all ages spend most of their time on social networking. As a result, vast amounts of information are being generated and exchanged through social networks worldwide. Moreover, the information shared through social networks and media spreads rapidly, nearly instantly, making it appealing to attackers to damage the transmission. Therefore, the privacy and security of social networks must be investigated from multiple perspectives, including security, privacy, and authenticity risks associated with the user's information shared whenever the user publishes personal data such as images, videos, audio, and more. Therefore, security and privacy are the major issues in social networks. To solve these issues, we propose machine learning-enabled distributed framework for attack detection in social networks. Extreme learning machine (ELM) algorithm is used at the edge layer with the classifier and train model for attack detection and communication latency in the networks. Furthermore, distributed blockchain is leveraged at the fog layer for data verification and validation, and then data is stored at the cloud layer. Moreover, we illustrate a methodological flowchart of the proposed framework.
AB - With rapidly evolving technology, social networks are the most popular medium for communicating information from person to person on the Internet. Nowadays, people of all ages spend most of their time on social networking. As a result, vast amounts of information are being generated and exchanged through social networks worldwide. Moreover, the information shared through social networks and media spreads rapidly, nearly instantly, making it appealing to attackers to damage the transmission. Therefore, the privacy and security of social networks must be investigated from multiple perspectives, including security, privacy, and authenticity risks associated with the user's information shared whenever the user publishes personal data such as images, videos, audio, and more. Therefore, security and privacy are the major issues in social networks. To solve these issues, we propose machine learning-enabled distributed framework for attack detection in social networks. Extreme learning machine (ELM) algorithm is used at the edge layer with the classifier and train model for attack detection and communication latency in the networks. Furthermore, distributed blockchain is leveraged at the fog layer for data verification and validation, and then data is stored at the cloud layer. Moreover, we illustrate a methodological flowchart of the proposed framework.
KW - Blockchain
KW - Machine learning
KW - Security and Privacy
KW - Social network
UR - https://www.scopus.com/pages/publications/85164030556
U2 - 10.1007/978-981-99-1252-0_39
DO - 10.1007/978-981-99-1252-0_39
M3 - Conference contribution
AN - SCOPUS:85164030556
SN - 9789819912513
T3 - Lecture Notes in Electrical Engineering
SP - 299
EP - 304
BT - Advances in Computer Science and Ubiquitous Computing - Proceedings of CUTE-CSA 2022
A2 - Park, Ji Su
A2 - Yang, Laurence T.
A2 - Pan, Yi
A2 - Pan, Yi
A2 - Park, Jong Hyuk
PB - Springer Science and Business Media Deutschland GmbH
T2 - 14th International Conference on Computer Science and its Applications, CSA 2022 and the 16th KIPS International Conference on Ubiquitous Information Technologies and Applications, CUTE 2022
Y2 - 19 December 2022 through 21 December 2022
ER -