Real-Time DDoS Attack Detection: Article Summary and Analysis

Verified

Added on  2020/04/01

|4
|648
|45
Report
AI Summary
This report summarizes an article focusing on a novel real-time DDoS attack detection mechanism based on the Multivariate Dimensionality Reduction Analysis (MDRA) algorithm within the context of Big Data. The article highlights the increasing threat of DDoS attacks, exacerbated by the rise of Big Data, and proposes the MDRA algorithm as an effective solution. The method involves three key components: traffic feature dimensionality reduction using the PCA method, traffic feature correlation analysis, and an attack detection framework. The report details the experimental setup, including dataset utilization and evaluation of key metrics such as Precision, TNR, FPR, and DR. The study compares the performance of the MDRA algorithm with previous approaches, emphasizing its efficiency and speed in detecting DDoS attacks. The report also includes a list of cited references that provides the source of information.
tabler-icon-diamond-filled.svg

Contribute Materials

Your contribution can guide someone’s learning journey. Share your documents today.
Document Page
Running head: SUMMARY OF ARTICLE
Summary of Article
Name of the Student
Student ID
Name of the University
Author’s Note:
tabler-icon-diamond-filled.svg

Secure Best Marks with AI Grader

Need help grading? Try our AI Grader for instant feedback on your assignments.
Document Page
1
SUMMARY OF ARTICLE
A Novel Real-Time DDoS Attack Detection Mechanism Based on MDRA Algorithm in Big
Data
Summary: The DoS attack, which occurs by a wide range of distributed computers, is known as
the Distributed Denial of Service or DDoS (Yu et al 2014). The Big Data technology has opened
more ways for DDoS attacks in any system. However, this type of attack can be reduced using
the Multivariate Dimensionality Reduction Analysis or MDRA algorithm.
The Denial of Service attack or DoS attack is the most significant attack in modern
world. It is a type of cyber attack, in which the hacker or the intruder seeks in a machine and
denies the service of the system. DDoS is a part of DoS attack (Joshi, Vijayan and Joshi 2012). It
consumes the network bandwidth, memory and CPU cycle of the attacked system. Previously,
there was a combined data mining approach for the detection of DDoS attack. It had an
automatic feature selection module. The Triangle Area Based Nearest Approach is another
approach for detecting this type of attack.
The real-time DDoS detection is done by following some of the steps like collecting
network traffic data sample and putting them into data acquisition system. Then the processed
traffic data is fed into Big Data system (Jia et al. 2016). The method mentioned in this article is
divided into three components, which are traffic feature dimensionality reduction, traffic feature
correlation analysis and attack detection framework based on MDRA algorithm. The PCA
method is utilized for extraction of less dimensional and more representative features.
The experiment of the MDRA algorithm is used by evaluating the data set and
pretreatment, experimental results and results comparisons in terms of time cost and resource
consumption (Alomari et al. 2012). The data set is taken into account at first and is then treated
Document Page
2
SUMMARY OF ARTICLE
in the first step. Next, four formulae is evaluated. These are the Precision, TNR, FPR and DR
(Jia et al. 2016). Then, the results are compared in terms of resource consumption and time cost.
DDoS attacks are extremely common in modern world. The Big Data technology has
opened more ways for DDoS attacks in any system. A real-time DDoS attack detection
mechanism is based on Multivariate Dimensionality Reduction Analysis or MDRA algorithm in
Big Data. In comparison with the previous approaches, this approach is more efficient and fast in
detecting the attacks.
Document Page
3
SUMMARY OF ARTICLE
References
Alomari, E., Manickam, S., Gupta, B.B., Karuppayah, S. and Alfaris, R., 2012. Botnet-based
distributed denial of service (DDoS) attacks on web servers: classification and art. arXiv preprint
arXiv:1208.0403.
Yu, S., Tian, Y., Guo, S. and Wu, D.O., 2014. Can we beat DDoS attacks in clouds?. IEEE
Transactions on Parallel and Distributed Systems, 25(9), pp.2245-2254.
Jia, B., Ma, Y., Huang, X., Lin, Z. and Sun, Y., 2016. A novel real-time ddos attack detection
mechanism based on MDRA algorithm in big data. Mathematical Problems in
Engineering, 2016.
Joshi, B., Vijayan, A.S. and Joshi, B.K., 2012, January. Securing cloud computing environment
against DDoS attacks. In Computer Communication and Informatics (ICCCI), 2012
International Conference on (pp. 1-5). IEEE.
chevron_up_icon
1 out of 4
circle_padding
hide_on_mobile
zoom_out_icon
logo.png

Your All-in-One AI-Powered Toolkit for Academic Success.

Available 24*7 on WhatsApp / Email

[object Object]