Retracted: Enhancing Collaborative Intrusion detection networks against insider attack using supervised learning technique

Singh, Rajesh; Deorari, Rajesh

doi:10.1109/mysurucon55714.2022.9972599

Cited by 2 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, the success of Log2Graph relies on the quality of feature engineering, the choice of relevant graph algorithms, and the adaptability to evolving threat VOLUME 4, 2016 scenarios. In another study employing graph neural network [34], the authors achieve robust anomaly-based insider threat detection using a Multi-Edge Weight Relational Graph Neural Network (MEWRGNN) approach. The technique combines GCN with anomaly detection to capture the contextual relationship of user behaviors over time, enabling accurate identification of insider threats.…”

Section: Learning-based Insider Detection Techniquesmentioning

confidence: 99%

“…Addressing these challenges requires a collaborative effort involving cybersecurity researchers, software developers, organizational leaders, and legal experts. The deployment of insider threat detection systems in real security environments demands a nuanced approach that considers not only technical aspects but also navigates the intricacies of organizational dynamics and regulatory landscapes [34], [39]. In conclusion, addressing malicious insider threats involves a multifaceted approach that combines technical solutions, employee training, and organizational policies.…”

Section: Challenges and Open Problemsmentioning

confidence: 99%

See 1 more Smart Citation

A Review of Recent Advances, Challenges, and Opportunities in Malicious Insider Threat Detection Using Machine Learning Methods

Alzaabi,

Mehmood

2024

IEEE Access

View full text Add to dashboard Cite

Insider threat detection has become a paramount concern in modern times where organizations strive to safeguard their sensitive information and critical assets from malicious actions by individuals with privileged access. This survey paper provides a comprehensive overview of insider threat detection, highlighting its significance in the current landscape of cybersecurity. The review encompasses a broad spectrum of methodologies and techniques, with a particular focus on classical machine-learning approaches and their limitations in effectively addressing the intricacies of insider threats. Furthermore, the survey explores the utilization of modern deep learning and natural language processing (NLP) based methods as promising alternatives, shedding light on their advantages over traditional methods. This analysis underscores the need for sophisticated solutions that can adapt to evolving threat landscapes and accommodate the intricacies of human behavior. In the conclusion section, the paper offers valuable insights into the future directions of insider threat detection. It advocates for the integration of more sophisticated time-series-based techniques, recognizing the importance of temporal patterns in insider threat behaviors. Additionally, the survey underscores the potential of NLP and large language model-based approaches, which can enhance threat detection by deciphering textual and contextual information. These recommendations reflect the evolving nature of insider threats and emphasize the need for proactive, datadriven strategies to safeguard organizations against internal security breaches. In conclusion, this survey not only underscores the urgency of addressing insider threats but also provides a roadmap for the adoption of advanced methodologies to enhance detection and mitigation capabilities in contemporary cybersecurity paradigms.

show abstract

Section: Learning-based Insider Detection Techniquesmentioning

confidence: 99%

Section: Challenges and Open Problemsmentioning

confidence: 99%

A Review of Recent Advances, Challenges, and Opportunities in Malicious Insider Threat Detection Using Machine Learning Methods

Alzaabi,

Mehmood

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…However, because workload is outsourced, this company also introduced new threats and attacks. The most pressing issues with cloud-based solutions are: a) an absence of information controls in mists that make veil intricacy issues for FSIs [17] on the grounds that private mists become standard in FinTech. Federated ML was the focus of work [18] and author [19] presentations of FL's current advanced and unsolved issues.…”

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

Retracted: Enhancing Collaborative Intrusion detection networks against insider attack using supervised learning technique

Cited by 2 publications

References 26 publications

A Review of Recent Advances, Challenges, and Opportunities in Malicious Insider Threat Detection Using Machine Learning Methods

A Review of Recent Advances, Challenges, and Opportunities in Malicious Insider Threat Detection Using Machine Learning Methods

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

Contact Info

Product

Resources

About