Cybersecurity And Artificial Intelligence: How AI Is Being Used in Cybersecurity To Improve Detection And Response To Cyber Threats
Main Article Content
Abstract
Aim: Cyberattacks continue to evolve and AI has the potential to detect these threats and respond in real time. The focus of this research paper will be to understand how AI is being applied to this end, addressing how AI assists in threat detection and incident response. The work focuses on the efficiency of different add-in AI techniques which are applied for identifying anomalies, automating incidents response and providing intelligent decision support.
Method: The research procedure incorporates an all-encompassing survey called literacy review and it is aimed at gathering existing information from both academic databases and industry reports. Quantitative and qualitative select human intelligence attributes are discussed by analysing case studies and real-world examples of AI powered cybersecurity systems. This approach applies numeric data processing and open-ended exploration in order to highlight the positive impact, negative aspects, and the most common emerging trends.
Results: The paper suggests that the AI-based, cybersecurity systems can highly facilitate threat detection accuracy, diminish response time and help in identifying the emerging phenomenon to some extent. The deep learning model, from particular research, was able to detect network intrusions more than 98% precisely, while a novel unsupervised machine learning algorithm has been successfully used for detecting up to 90% of undetected malware samples. Quantitative data gives us perspective on both the benefits like increased efficiency, a scalable platform, proactive threat detection, and continuous learning, and the obstacles, including the question of quality of the data, bias of models, and the necessity of the human factor (Using Artificial Intelligence in Cybersecurity | Balbix, 2016).
Conclusion: The incorporation of AI technologies in cybersecurity techniques might able to actually be a game-changer for the manner we spot out threats and react to incidents. Although quantitative and qualitative outcomes highlight the pros of the AIbased cybersecurity systems, one should account for challenges and disadvantages that might disrupt its responsible and useful use. In conclusion, platform provides recommendations on future research, covering issues of longitudinal studies, adversarial machine learning, explainable AI, and human-AI collaboration.
Downloads
Metrics
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format for any purpose, even commercially.
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms.
Under the following terms:
- Attribution — You must give appropriate credit , provide a link to the license, and indicate if changes were made . You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
Notices:
You do not have to comply with the license for elements of the material in the public domain or where your use is permitted by an applicable exception or limitation .
No warranties are given. The license may not give you all of the permissions necessary for your intended use. For example, other rights such as publicity, privacy, or moral rights may limit how you use the material.
References
Apruzzese, A., Sliepsteen, F., & Garcia-Alfaro, P. (2017, April). Security and privacy issues in machine
learning for cyber security. In 2017 IEEE Conference on Communications and Network Security (CNS)
(pp. 1-8). IEEE.
Cisco. (2017). The cybersecurity imperative: A business transformation journey to the cloud. [White paper]
European Cybersecurity Certification Board (ECC University). (2017). Artificial intelligence in
cybersecurity. [White paper]
Fortinet. (n.d.). How artificial intelligence (AI) can help with cybersecurity threats. [Blog post] Retrieved
from IBM. (n.d.). Artificial intelligence (AI) cybersecurity. [Webpage] Retrieved from
Jada, Y. M., & Mayayise, O. S. (2017, December). Explainable artificial intelligence for cyber security: A
survey. In 2017 International Conference on Computational Science and Computational Intelligence
(CSCI) (pp. 1471-1477). IEEE.
Ji, Q., Guo, Y., Zhang, X., & Yu, Y. (2018, January). A survey on knowledge graphs for cybersecurity.
IEEE Access, 6, 17734-17748.
Kaur, P., Sandhu, M. S., & Singh, M. (2017a, July). A survey on machine learning for cloud security. In
International Conference on Computing, Communication and Security (ICCCS) (pp. 1-6). IEEE.
Kaur, P., Sandhu, M. S., & Singh, M. (2017b, November). A survey on machine learning for cloud security.
Journal of Network and Computer Applications, 90, 144-152.
LeewayHertz. (2015, June 23). AI in fraud detection: Enhancing security. [Blog post] Retrieved from
Libeer, G. (2018, January 10). 5 Cybersecurity trends you should be aware of in 2018. Help Net Security.
Retrieved from
McKinsey & Company. (2018, January). Beyond the hype: The payback from AI in cyber security.
[Report]
Al-Shamery, K., Ahmad, A., & Idris, N. A. (2018). Machine learning for network anomaly detection: A
survey. Computers & Security, 74, 11-28.
Balbix. (2016). Using artificial intelligence in cybersecurity. [White paper] Retrieved from [Source
unavailable]
Goh, T., Lee, C., & Bressan, M. (2017). An introduction to deep learning in natural language processing.
Morgan & Claypool Publishers.
Gupta, D., & Shanker, B. (2018). A survey of intrusion detection systems using machine learning.
International Journal of Computer Applications, 178(13), 10-15.
Hammer, A., & Sullivan, M. (2017). A survey of machine learning techniques for phishing detection. In
Cybersecurity (pp. 149-168). Springer, Cham.
Huang, Y., Cheng, S., & Zhang, Y. (2017, December). Deep learning for network anomaly detection: An
overview. In 2017 IEEE International Conference on Computational Science and Computational
Intelligence (CSCI) (pp. 1434-1439). IEEE.
James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An introduction to statistical learning (Vol. 112).
Springer.
Langford, J., & McAfee, A. (2017, February). Machine learning in the cloud. O'Reilly Media, Inc.
Lazarevic, A., & Kumar, V. (2005). Intrusion detection systems based on sequential patterns. In
Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data
mining (pp. 563-572). ACM.
McIntosh, M., & Vigurs, K. (2018). A survey of phishing detection techniques. Computers & Security, 73,
-307.
Mehmood, A., Hassan, S. F., & Rahman, S. U. (2017). Deep learning for anomaly detection: A survey.
Journal of Network and Computer Applications, 108, 224-245.
Meng, G., Xu, Y., Zhang, H., Sun, C., & Wang, Y. (2018). Deep learning for anomaly detection in wireless
sensor networks: A survey. Neurocomputing, 279, 613-628.
Mittal, S., & Gupta, A. (2018). A survey on machine learning based network intrusion detection systems.
Network Security and Applications, 11(1), 78-88.
Pasquale, F. (2015). The black box society: The secret algorithms that control money and information.
Harvard University Press.
Russell, S. J., & Norvig, P. (2016). Artificial intelligence: A modern approach (3rd ed.). Pearson Education
Limited.
Sheng, S., Tan, Y., Wang, X., & Deng, R. (2018). A survey on the applications of machine learning in
internet of things. Journal of Network and Computer Applications, 109, 88-108.