Retracted: Design of IoT network using Deep learning model for Anomaly Detection

Rana, Arti; Srivastava, Vineet Kishore

doi:10.1109/mysurucon55714.2022.9971800

Cited by 1 publication

(2 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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. The summary based on the existing technique is added in Table 1.…”

Section: Existing Fintech Intrusion Detection Systemmentioning

confidence: 99%

See 1 more Smart Citation

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%

“…The method of moments achieves the simplest form on a discrete maximum likelihood function by using the approximated PDF indicated above rather than the actual transitional PDF g(S n+1 |S n t; nθ) in Equations ( 21)- (23).…”

Section: Fintech Intrusion Detection Based Iot Module Using Cyber Thr...mentioning

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

show abstract

Retracted: Design of IoT network using Deep learning model for Anomaly Detection

Cited by 1 publication

References 28 publications

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

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

Contact Info

Product

Resources

About