Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Journal of Robotics and Control (JRC) Applied Research and Smart Technology (ARSTech)
Kevin Curran
Ulster University, School of Computing and Intelligent Systems, Londonderry, Northern Ireland
Aerospace Engineering Automotive Engineering Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering Materials Science & Nanotechnology Mechanical Engineering Physics

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Mitigating Denial of Service Attacks with Load Balancing Ezenwe, Adaoma; Furey, Eoghan; Curran, Kevin
Journal of Robotics and Control (JRC) Vol 1, No 4 (2020): July
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.1427

Abstract

Denial of service (DoS) attack continues to pose a huge risk to online businesses. The attack has moved from attack at the network level – layer 3 and layer 4 to the layer 7 of the OSI model. This layer 7 attack or application layer attack is not easily detectable by firewalls and most intrusion Detection systems and other security tools but have the capability of bringing down a well-equipped web server. The wide availability and easy accessibility of the attack tools makes this type of security risk very easy to execute, very prolific and difficult to completely mitigate. There have been an increasing number of such attacks against the web server infrastructures of many organisations being recorded. The aim of this research is to look at some layer 7 application DDoS attack tools and test open source tools that offer some form of defense against these attacks. The research deployed open source load balancing software, HAProxy as a first line of defense against Denial of Service attack. The three components of the popular free open source data analysis tool, Elastic stack framework- Logstash, Elasticsearch and Kibana were used to collect logs from the web server, filter and query the logs and then display results in dashboards and graphs to help in the identification of an attack by analysing the visually displayed log data. Rules are also setup to alert the business of anomalies detected based on pre-determined benchmarks.
Identification of stock market manipulation using a hybrid ensemble approach Quinn, Pearse; Toman, Marinus; Curran, Kevin
Applied Research and Smart Technology (ARSTech) Vol. 4 No. 2 (2023): Applied Research and Smart Technology
Publisher : Universitas Muhammadiyah Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23917/arstech.v4i2.2576

Abstract

Anomaly detection in time series data is a complex data mining issue with many useful, real-world applications. Anomalies in datasets represent deviations in the expected behaviour of a system and can indicate rare but significant events that require intervention. Market manipulation is a serious issue in financial jurisdictions worldwide, with financial regulators such as the SEC constantly trying to prevent it and prosecute those guilty of it. This paper makes use of state-of-the-art deep learning techniques as well as more classical statistical techniques in order to detect anomalies in five real-world datasets. The predictions of these models are then aggregated in two different ensemble models. The results of the individual models as well as the ensemble models, are evaluated, and F1-Score measures performance. Nine individual models, consisting of three models based on LSTM with Dynamic Thresholding, three ARIMA models and three Exponential Smoothing models, were used to generate predictions of anomalies based on daily trading volumes. The individual predictions of these models were then aggregated, with two different ensemble methods being used, namely the majority voting ensemble method and the ensemble averaging aggregation method. While both performed well, the majority voting ensemble method was seen to be the superior method in this study, with an average F1Score of 0.494, compared to an F1Score of 0.414 for the ensemble averaging aggregation method.
Co-Authors Ezenwe, Adaoma Furey, Eoghan Quinn, Pearse Toman, Marinus