Autonomous Response Systems in Cybersecurity: A Systematic Review of AI-Driven Automation Tools

Abstract

Generally, it has been observed that there is a growing need for strong security solutions that can safeguard and improve the dependability of autonomous systems. Thus, this study examined the autonomous response systems in cybersecurity using a systematic review to understand AI-driven automation tools. The study adopts a qualitative systematic review design. Using the Preferred Reporting Items for Systematic Reviews and Meta-analysis (PRISMA), the study adopted a structured approach to search for relevant literature. The final selected literature for the study is sixteen (16). The findings showed that machine learning, deep learning, and natural language processing models are used by organizations to implement AI-driven autonomous response systems. It also emphasized the use of anomaly detection, behavioural analytics, autonomous incident responses, SISMECA, and ontology-based models for securing autonomous transport systems. Results showed that both supervised and unsupervised learning approaches are used for algorithms and methodologies in AI-driven autonomous cybersecurity response systems. Findings showed that AI-driven systems are effective in the mitigation of cyber threats. Results indicate that challenges faced in the deployment of AI-driven autonomous response systems in cybersecurity include adversarial machine learning techniques and the dual-use dilemma. Findings showed that the ethical considerations associated with the deployment of AI-driven autonomous response systems in cybersecurity include collaboration, transparency, and accountability. The study concludes that autonomous response systems are highly effective in cybersecurity. However, there are ethical issues that should be considered in the deployment of the systems.