AI in the Trenches: How Machine Learning is Fighting Cybercrime |
||
 |
 |
|
| © 2024 by IJCTT Journal | ||
| Volume-72 Issue-10 |
||
| Year of Publication : 2024 | ||
| Authors : Sriharsha Daram | ||
| DOI : 10.14445/22312803/IJCTT-V72I10P125 | ||
How to Cite?
Sriharsha Daram, "AI in the Trenches: How Machine Learning is Fighting Cybercrime," International Journal of Computer Trends and Technology, vol. 72, no. 10, pp. 183-191, 2024. Crossref, https://doi.org/10.14445/22312803/IJCTT-V72I10P125
Abstract
Cybersecurity threats increased incidents, and the sophistication of the development of superior countermeasures has never been more significant. Although not powerless in detecting or preventing threats, conventional security solutions currently available are insufficient in combating complex attacks like ransomware, phishing, and zero-day attacks. To overcome this, Artificial Intelligence (AI) and Machine Learning (ML) are the key technologies enabling cybersecurity by implementing automated tools for detecting and preventing such attacks. Compared to rule-based systems, AI applications can be updated and modified, which sets them as optimal for anomaly detection, pattern finding, and predictive evaluation. They all take vast volumes of data and process it in near real-time, and are able to pick out patterns or features that may indicate signs of attack, enabling more accurate and quicker threat detection. However, incorporating AI and ML in cybersecurity is not without its hurdles; training and validating such systems involves inputting a large volume of data, especially personally identifiable and organizational data. Further, the ability to scale the model can also be a challenge since AI models have to perform well in various network environments to prevent, detect, and respond to a range of threats without slowing down the system. In addition, issues of adversarial attacks on the machine learning models in which the attackers ensure that they provide data that the AI system will find hard to decipher qualify as a serious threat due to their impact on the reliability of these systems. Thus, despite its effectiveness in the field of cybersecurity, it is relevant to note that the constant enhancement of the applied technologies is the key to further protection against new and more complex cyber threats.
Keywords
Artificial Intelligence, Machine Learning, Cybersecurity, Cybercrime, Anomaly Detection, Adversarial Attacks, Data Privacy.
Reference
[1] Anna L. Buczak, and Erhan Guven, “A Survey of Data Mining and Machine Learning Methods for Cyber Security Intrusion Detection,” IEEE Communications Surveys & Tutorials, vol. 18, no. 2, pp. 1153-1176, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Nicolas Papernot et al., “Practical Black-Box Attacks against Machine Learning,” Proceedings of the 2017 ACM on Asia Conference on Computer and Communications Security, pp. 506-519, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[3] AI in Cybersecurity – Uses, Benefits and Challenges, 2024. [Online]. Available: https://www.geeksforgeeks.org/ai-in-cybersecurity/
[4] Ian J. Goodfellow, Jonathon Shlens, and Christian Szegedy, “Explaining and Harnessing Adversarial Examples,” Arxiv, pp. 1-11, 2014.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Battista Biggio, and Fabio Roli, “Wild Patterns: Ten Years after the Rise of Adversarial Machine Learning,” Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security, Toronto Canada, pp. 2154-2156, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Jitender K. Malik, and Sanjaya Choudhury, “A Brief Review on Cyber Crime-Growth and Evolution,” Pramana Research Journal, vol. 9, no. 3, pp. 242-278, 2019.
[Google Scholar]
[7] L. Chimchiuri, “The Evolution of Cybercrime Legislation,” Scientific works of National Aviation University. Series: Law Journal Air and Space Law, vol. 2, no. 71, pp. 221-227, 2024.
[Google Scholar]
[8] Peter Grabosky, “The 2 Evolution of Cybercrime, 2006-2016,” Cybercrime Through an Interdisciplinary Lens, 2016.
[Google Scholar] [Publisher Link]
[9] Nadine Wirkuttis, and Hadas Klein, “Artificial Intelligence in Cybersecurity,” Cyber, Intelligence, and Security, vol. 1, no. 1, pp. 103 119, 2017.
[Google Scholar]
[10] Pranav Patil, “Artificial Intelligence in Cybersecurity,” International Journal of Research in Computer Applications and Robotics, vol. 4, no. 5, pp. 1-5, 2016.
[Google Scholar]
[11] Rupa Ch et al., “Computational System to Classify Cyber-crime Offenses using Machine Learning,” Sustainability, vol. 12, no. 10, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Javier Martínez Torres, Carla Iglesias Comesaña, and Paulino J. García-Nieto, “Machine Learning Techniques Applied to Cybersecurity,” International Journal of Machine Learning and Cybernetics, vol. 10, pp. 2823-2836, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Kamran Shaukat et al., “A Survey on Machine Learning Techniques for Cyber Security in the Last Decade,” IEEE Access, vol. 8, pp. 222310-222354, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Kamran Shaukat et al., “Performance Comparison and Current Challenges of using Machine Learning Techniques in Cybersecurity,” Energies, vol. 13, no. 10, pp. 1-27, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Pooja Kamat, and Apurv Singh Gautam, Recent Trends in The Era of Cybercrime and The Measures to Control Them, 1st ed., Handbook of e-Business Security, Auerbach Publications, pp. 1-16, 2018.
[Google Scholar] [Publisher Link]
[16] Aleksandra Kuzior et al., “Cybersecurity and Cybercrime: Current Trends and Threats,” Journal of International Studies, vol. 17, no. 2, pp. 220-239, 2024.
[Google Scholar] [Publisher Link]
[17] M.J. Schlegel, “A Handbook of Instructional and Training Program Design,” ERIC, 1995.
[Google Scholar] [Publisher Link]
[18] Shashank J. Thanki, and Jitesh J. Thakkar, “Value–value Load Diagram: A Graphical Tool for Lean–Green Performance Assessment,” Production Planning & Control, vol. 27, no. 15, pp. 1280-1297, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Sushma Kulkarni, “Graph Theory and Matrix Approach for Performance Evaluation of TQM in Indian Industries,” The TQM Magazine, vol. 17, no. 6, pp. 509-526, 2005.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Gabriel Kabanda, Colletor Tendeukai Chipfumbu, and Tinashe Chingoriwo, “A Reinforcement Learning Paradigm for Cybersecurity Education and Training,” Oriental Journal of Computer Science and Technology, vol. 16, no. 1, pp. 12-45, 2023.
[Google Scholar]
[21] Ram Shankar Siva Kumar et al., “Adversarial Machine Learning-Industry Perspectives,” 2020 IEEE Security and Privacy Workshops (SPW), San Francisco, CA, USA, pp. 69-75, 2020.
[CrossRef] [Google Scholar] [Publisher Link]