Content uploaded by Alpana Singh
Author content
All content in this area was uploaded by Alpana Singh on Nov 09, 2023
Content may be subject to copyright.
1
Big Data Technologies for Cyber Security in the Digital Era
Alapna Singh1
1Wipro Technologies Ltd, Hyderabad, India
1alpanasingh8@gmail.com
August 2021
Abstract: The current research aims to identify some of the applications of big data technologies
in cybersecurity in the digital era. The world is today considered to have transformed and become
a digital space. The overall focus on digital transactions and devices has all contributed towards
making big data technologies necessary in cyber security. The study follows a TAM model, which
identifies that the application of big data technologies for cyber security depends on their ease of
use and usefulness. The paper then adopts a qualitative research design by reviewing information
from acceptable sources. The paper then discusses and concludes by supporting the need for more
research within this field.
Keywords: Big data, cyber security, cyber-attacks, IoT, digital era, data analytics, log analysis.
I. Introduction
Cybersecurity has become an essential and critical factor in the success of organizations today.
Businesses are, therefore, identifying more effective and critical ways through which they can
improve their cybersecurity. Rajasekharaiah et al. (2020) identify that the emerging trends in
cybersecurity have been promoted by the increasing risks associated with cybercrimes. Most
businesses depend on the Internet for their operations. The overall focus on cybersecurity is aimed
to improve and protect business operations from attackers who could affect the company's success.
Cybersecurity has become increasingly critical in business growth and success because of its role
in promoting business success.
Big data describes the vast amounts of data that organizations are collecting every day. The overall
rise in information technology adoption has pushed businesses to hold and control significant
amounts of data (Yi & Li, 2017). This data is considered critical in promoting business operations
if used correctly (Dash et. al., 2019). Big data technologies describe the technologies that can
analyze and obtain meaning from vast amounts of data organizations store (Petrenko, 2018). Big
data technologies are therefore crucial for providing insights from the data, which reflect on
changes in the industry or within the company. Big data technologies have proven critical and
effective in other emerging technologies and industries that depend on information technology.
The Internet of Things (IoT) is considered one of the revolutionary technologies whose use is
growing significantly across various sectors. Big data technologies are becoming more impactful,
with more data being collected by IoT devices. Big data technologies are also considered essential
in cyber security operations (Petrenko, 2018). The ability to collect data at scale and obtain patterns
from this data proves to be an effective cybersecurity solution. Cybersecurity systems have been
identified to benefit from big data analytics. There are different areas in which big data analytics
can be implemented to promote cybersecurity. Big data processing and analytical strategies are
crucial to improving cybersecurity actions. In this study we will address the below research
questions.
2
Research Question:
1. How have big data technologies contributed to and impacted cybersecurity in the digital
era?
2. What are the essential implications of big data technologies in cyber security ?
II. Objectives
• To analyze cybersecurity trends in the digital era.
• To describe applications of big data technologies in cybersecurity.
• To identify the future of big data technologies in cyber security.
III. Literature Review
Big data has become a crucial technology in today's world. This has been attributed to the overall
rise in data use. Companies produce enormous amounts of data daily (Rajasekharaiah et al., 2020).
This data has become crucial in how a company can guide its operations and improve its practices.
Figure 1 below identifies the overall stages associated with data processing in big data. The image
shows that big data processing takes data through several stages before it becomes useful (Cesario,
2019). The overall success of big data has been attributed to legacy database systems' inability to
handle the vast data being produced.
Figure 1: Big Data Processing Stages
The different stages associated with data processing identified above engage different technologies
and tools. Using different technologies and tools has proven to be a reliable approach through
which organizations can make sense of vast amounts of data they control. Predictive analysis has
become a common application associated with big data (Cesario, 2019). Companies are today
focused on predicting some of the changes that are to be expected with most of their decisions
(Rajasekharaiah et al., 2020; Dash et. al., 2018). Companies that adopt big data technologies can
now improve customer experience, improve operational efficiency, and provide new revenue
opportunities. Recent interest has showcased the need to implement big data technologies in
cybersecurity remains a significant concern for organizations. The overall concern for
cybersecurity has been attributed to the overall growth associated with technology. Cybercrime is
now a significant issue many organizations and governments strive to avoid. The probability
associated with cyber-attacks today has significantly gone higher due to the rise in skills and
technology (Bachupally et al., 2016). Cyber security continues to be a major concern because big
data is also growing. The aim and objective of most cyber attacks is to gain information. Big data
technologies have, therefore, depended on cyber security measures to ensure that cyber-attacks are
overcome and that data has been protected.
The emergence of big data technology proved to be a crucial advantage in cyber security.
Information security is identified to have become a big data analytics problem. The meaningful
3
patterns associated with big data analytics can be used to address security risks and persistent
threats identified in an organization (Bachupally et al., 2016). Intrusion weaknesses are also
potentially addressed using big data analytics tools. Such tools have proven relevant and
significant in addressing common cyber-attacks.
Big data analytics is a key concept critical in cyber security. Figure 2 below showcases the different
ways that Big data analytics has been effective in combatting attacks. The technology has proven
critical based on its ability to collect large amounts of information and identify insights from the
data (Krishnan & Thampi, 2020). Attacks such as hacking, Malware, social attacks, and human
errors are all avoided using big data technologies. Figure 2 identifies how each of these risks and
threats are protected under big data analytics.
Figure 2: Common cyber-attacks addressed using big data analytics
There is still a significant gap in identifying the exact approach and impact of big data analytics in
cyber security. Extensive research, as showcased above, does not go into detail on the way cyber
security depends on big data analytics (Kantarcioglu & Xi, 2016). The current study is aimed at
reviewing current literature and identifying the impact of big data technologies in cybersecurity in
the current era. The overall focus will be to showcase how current literature identifies the
applications of big data technologies in cyber security. The overall impact of cyber security in
developing big data technologies will also be described.
IV. Methodology
Theoretical Framework
The study is guided by the Technology Acceptance Model theory. The model identifies that a
technology is used based on two main factors. These factors include the ease of use associated
with the technology system and the usefulness associated with the technology (Inayatulloh, 2020).
Cyber security being dependent on big data technology, therefore, means that the technologies
should be useful. The TAM model will be used to showcase whether big data technologies are
useful enough and whether they have an impact on cyber security. The ease of use of big data
technologies for cyber security measures also signifies another critical factor in how cyber security
is influenced. Figure 3 below identifies the TAM model and showcases the exact factors that
influence the use of Big data technologies in cyber security.
4
Figure 3: Theoretical Framework (TAM Model)
The model identifies that for big data technologies to be effective in cyber security, factors such as
their usefulness, ease of use, attitude, and behavioral intention will influence the entire process
(Inayatulloh, 2020).
V. Data Collection
The study adopts a critical review methodology. This methodology approach is guided by
reviewing existing research from reputable secondary sources. Books and journal articles will be
used as key sources for obtaining the information needed (Averill, 2014). The study, therefore,
engages a qualitative research approach guided by qualitative design measures (Averill, 2014). The
results associated with this methodology will be presented systematically, allowing the intended
audience to grasp what methodology was adopted and how the data collected answers the research
question and the various objectives identified.
VI. Results
Big data analytics for cybersecurity describes the use of technologies and tools aimed at protecting
computer systems from advanced cyber threats (Harrison, 2017). The different big data analytics
technologies can be identified in web, mobile, and software systems, each aimed at promoting and
improving the current state of computer systems (Harrison, 2017). big data analytics technologies
are considered critical in the various processes engaged in cyber security. Cyber security processes
such as finding and stopping cyber threats can be accomplished through big data technologies.
This is considered a major factor in how big data technologies can be used to improve cyber
security processes.
Several systems have been developed over the years to promote cyber security. Systems such as
the one introduced by Xu et al. (2016) aim to detect anomalies by analyzing system log data.
System log data is considered strenuous for humans to understand and keep track of. The system,
however, developed a reduction technique through which information could be identified through
big data technologies to detect anomalies. Hossain et al. also introduced a critical system that could
improve the efficiency of forensic analysis without undermining the accuracy associated with the
process involved (Harrison, 2017). The analysis involved the reduction technique necessary to
provide forensic analysts with a summary of the log data without undermining the accuracy
required in investigating cyber-attacks.
Bilge et al. (2017) introduced a system 2017 that focused on predicting risks associated with
cybersecurity systems. The system, named the Risk Teller, focused on identifying binary files
5
within a machine log and identifying the infection risks associated with the machine. The system
was considered especially effective in promoting an understanding of the machines, protecting
them from possible future attacks. The system also relied on big data analytics technologies to
analyze and make sense of the machine logs.
Deep learning, a significant component of big data analytics, was also adopted in a system for
anomaly detection introduced in 2017. Du et al. (2017) developed a DeepLog system to obtain
relevant insights from a system's data set and predict some weaknesses that could be utilized
against the system (Krishnan & Thampi, 2020). The overall objective of the system was effectively
achieved by integrating big data analytics technologies to make sense of the vast system logs
obtained from a computer system.
The various systems identified above are technologies that have been introduced to depend on big
data analytics in promoting cyber security. For example, Nilizadeh et al. (2017) introduced a
Twitter analytics system named POISED to review malicious messages from Twitter and identify
Spam messages. The system was tested and identified to have a 91% success rate.
The analysis identifies that there have been various applications associated with big data in cyber
security. The main focus was promoting intrusion and anomaly detection systems and Malware
and ransomware detection systems (Nilizadeh et al., 2017). Big data analytics has also proven
critical in cloud security and spam and phishing detection. Big data analytics is, therefore, a crucial
tool and technology in cyber security. Future cyber security systems will be heavily dependent on
cyber security. The systems will process large amounts of data collected from IoT devices.
VII. Discussion
Big data technologies have a vast number of applications, which make them critical and essential
in cyber security (Sharma & Dash, 2020). The main benefit associated with big data technologies
is the ability to promote threat detection and response (Nilizadeh et al., 2017). The ability to detect
and respond to digital threats is achieved by the ability to process a significant amount of data at a
moment's notice and make sense of all of it, which has made big data technologies crucial
(Nilizadeh et al., 2017). Another key advantage associated with big data technologies is the ability
to reduce false alarms.
Cyber security forensics is another field of cyber security that has benefited from the integration
of big data technologies. The field of analytics is sometimes overwhelmed by the need to review
and analyze vast amounts of data (Hashmani et al., 2018). The data analysis is focused on
reviewing large amounts of data to understand and make sense of the information (Nilizadeh et al.,
2017). Forensic scientists today can implement big data technologies to obtain insights to identify
which parties are responsible for an attack. This advantage also showcases the impact that big data
technologies have had on cyber security in the digital era (Krishnan & Thampi, 2020). Many
studies also showcase that cyber security in the future will be dependent on big data technologies.
VIII. Conclusion
In conclusion, big data technologies have become a critical tool in cyber security in the digital era
today. The overall rise in big data technology trends has made them a significant tool within the
cyber security space. Big data analytics effectively predicts attacks before they happen, allowing
for more convenient measures to be adopted. The analysis focused on reviewing various articles
and identifying some of the cyber security systems that have been developed recently to depend
6
on big data technologies. Big data technologies are, therefore, significant and critical tools needed
to promote cyber security in the digital era.
The main limitation identified in the current study is that it was limited to current applications of
big data technologies in cyber security. The study overlooked some of the changes and trends
within cyber security. Future research should focus on identifying the future implications
associated with advancements in big data technologies. There have been several trends identified
in big data technologies. These trends have proven critical in making big data technologies more
efficient. Studies should, therefore, focus on identifying what are some of the implications that
these changes will have over cyber security.
References
Averill, J. B. (2014). Qualitative Data Analysis. Nursing Research Using Data Analysis.
https://doi.org/10.1891/9780826126894.0001
Bachupally, Y. R., Yuan, X., & Roy, K. (2016). Network security analysis using Big Data
Technology. SoutheastCon 2016. https://doi.org/10.1109/secon.2016.7506686
Bilge, L., Han, Y., & Dell’Amico, M. (2017). Riskteller. Proceedings of the 2017 ACM SIGSAC
Conference on Computer and Communications Security.
https://doi.org/10.1145/3133956.3134022
Cesario, E. (2019). Big Data Analysis for Smart City Applications. Encyclopedia of Big Data
Technologies, 152–158. https://doi.org/10.1007/978-3-319-77525-8_140
Dash, B., Sharma, P., & Ansari, M. F. (2018). A Data-Driven AI Framework to Improve Urban
Mobility and Traffic Congestion in Smart Cities. https://doi.org/10.5281/zenodo.8364853
Dash, B., Sharma, P., & Swayamsiddha, S. (2019). Resilience or Resistance? Outreach of Big
Data in the Digital Age.
Du, M., Li, F., Zheng, G., & Srikumar, V. (2017). Deeplog. Proceedings of the 2017 ACM
SIGSAC Conference on Computer and Communications Security.
https://doi.org/10.1145/3133956.3134015
Harrison, L. (2017). Data Visualization for cybersecurity. Big Data Analytics in Cybersecurity,
99–114. https://doi.org/10.1201/9781315154374-5
Hashmani, M. A., Muslim, S., M., A., Zaffar, M., & Raza, K. (2018). An ensemble approach to
Big Data Security (cyber security). International Journal of Advanced Computer Science and
Applications, 9(9). https://doi.org/10.14569/ijacsa.2018.090910
Inayatulloh. (2020). Technology acceptance model (TAM) for implementing knowledge acquired
model for SME. 2020 International Conference on Information Management and Technology
(ICIMTech). https://doi.org/10.1109/icimtech50083.2020.9211279
Kantarcioglu, M., & Xi, B. (2016). Adversarial Data Mining. Proceedings of the 2016 ACM
SIGSAC Conference on Computer and Communications Security.
https://doi.org/10.1145/2976749.2976753
7
Krishnan, K. S., & Thampi, S. M. (2020). Deep Learning Approaches for IOT Security in the Big
Data Era. Advanced Sciences and Technologies for Security Applications, 105–135.
https://doi.org/10.1007/978-3-030-35642-2_6
Nilizadeh, S., Labrèche, F., Sedighian, A., Zand, A., Fernandez, J., Kruegel, C., Stringhini, G., &
Vigna, G. (2017). Poised. Proceedings of the 2017 ACM SIGSAC Conference on Computer
and Communications Security. https://doi.org/10.1145/3133956.3134055
Petrenko, S. (2018). Big Data Technologies for Monitoring of Computer Security: A Case Study
of the Russian Federation. https://doi.org/10.1007/978-3-319-79036-7
Rajasekharaiah, K. M., Dule, C. S., & Sudarshan, E. (2020). Cyber security challenges and its
emerging trends on the latest technologies. IOP Conference Series: Materials Science and
Engineering, 981(2), 022062. https://doi.org/10.1088/1757-899x/981/2/022062
Sharma, P., & Dash, B. (2020). Big Data-IoE Relationships and the Future of Smart Cities.
Xu, Z., Wu, Z., Li, Z., Jee, K., Rhee, J., Xiao, X., Xu, F., Wang, H., & Jiang, G. (2016). High
Fidelity Data Reduction for Big Data Security Dependency analyses. Proceedings of the
2016 ACM SIGSAC Conference on Computer and Communications Security.
https://doi.org/10.1145/2976749.2978378
Yi, S., & Li, Q. (2017). Big Data Analytics for Security in Fog Computing. Big Data Analytics in
Cybersecurity, 245–262. https://doi.org/10.1201/9781315154374-11
