Retracted: Multilayer Statistical Intrusion Detection Model for Wireless Network

Gehlot, Anita; Joshi, Ankita

doi:10.1109/mysurucon55714.2022.9972477

Cited by 1 publication

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In mobile-edge computing (MEC), author [21] provided an overview of FL chain's concepts and opportunities. Author [22] provided a comprehensive analysis of FL privacy and security that has the potential to help bridge the gap between the current state of federated AI (FAI)and the future. Work [23] discussed the privacy issue and preservation measures surrounding the integration of BT and FL for IoT.…”

Section: Existing Fintech Intrusion Detection Systemmentioning

confidence: 99%

Cloud-Based Smart Contract Analysis in FinTech Using IoT-Integrated Federated Learning in Intrusion Detection

Kollu

Janarthanan²,

Karupusamy³

et al. 2023

Data

View full text Add to dashboard Cite

Data sharing is proposed because the issue of data islands hinders advancement of artificial intelligence technology in the 5G era. Sharing high-quality data has a direct impact on how well machine-learning models work, but there will always be misuse and leakage of data. The field of financial technology, or FinTech, has received a lot of attention and is growing quickly. This field has seen the introduction of new terms as a result of its ongoing expansion. One example of such terminology is “FinTech”. This term is used to describe a variety of procedures utilized frequently in the financial technology industry. This study aims to create a cloud-based intrusion detection system based on IoT federated learning architecture as well as smart contract analysis. This study proposes a novel method for detecting intrusions using a cyber-threat federated graphical authentication system and cloud-based smart contracts in FinTech data. Users are required to create a route on a world map as their credentials under this scheme. We had 120 people participate in the evaluation, 60 of whom had a background in finance or FinTech. The simulation was then carried out in Python using a variety of FinTech cyber-attack datasets for accuracy, precision, recall, F-measure, AUC (Area under the ROC Curve), trust value, scalability, and integrity. The proposed technique attained accuracy of 95%, precision of 85%, RMSE of 59%, recall of 68%, F-measure of 83%, AUC of 79%, trust value of 65%, scalability of 91%, and integrity of 83%.

show abstract

Section: Existing Fintech Intrusion Detection Systemmentioning

confidence: 99%