Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{169990,
        author = {AKSHAYA K and Aditi Singh and B. Manimekala},
        title = {ADVERSARIAL MACHINE LEARNING IN CYBERSECURITY},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {6},
        pages = {3347-3354},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=169990},
        abstract = {Adversarial examples are those inputs designed to deceive ML systems into making wrong predictions. Adaptation of machine learning in computer systems seriously raises several concerns about this manipulative behavior. This survey revisits 50 key works that have shaped Adversarial Machine Learning, focusing on its use in Cyber Security. The survey categorizes texts into key themes such as adversarial attack strategies, defense mechanisms, case studies, frameworks, and trends. It generally synthesizes the current state of the field on how attackers can compromise ML systems and their corresponding countermeasures. Perhaps the most important finding of this review is a gap between the theoretical developments in AML and their practical implementation. While lots of defense strategies have emerged, most of them remain untried under real-world conditions. Also, the efficiency of antimalware is bound to a specific model or type of attack, a factor that poses gendered questions in various other corners of cyber security. The researchers indicate that assessing AML defenses is hard to trace due to the lack of a measurement metric specified. Due to inconsistency, the studies vary, and it becomes hard to assess progress in that area. Therefore, this paper identifies ample opportunities for future research, since the significant limitations observed in deploying machine learning algorithms have been considered. That will be the implementation of different security measures for all the varied devices accessing the Internet or any other network, including cloud computing, using standard tools and anti-malware software.},
        keywords = {Adversarial machine learning, Cyber Security, Adversarial Attacks, Defense Mechanisms, Anti-malware solutions.},
        month = {November},
        }