Published Paper Details:

The increasing rate and complexity of cyberattacks in the financial industry have required the implementation of more robust cybersecurity technologies. Traditional threat detection technologies are not adequate in managing the dynamic nature of such attacks, hence the need for more advanced systems. This study investigates the convergence of Observability-Driven Cybersecurity and Artificial Intelligence (AI) technologies and the use of technologies like AppDynamics towards advanced threat detection in financial IT systems. Despite the growing adoption of AI and observability technologies, there is a broad research gap on how such technologies can be synergistically combined to offer proactive security solutions in real-time, particularly in the high-risk and complex environment of financial institutions. Current systems are ineffective in detecting advanced persistent threats (APTs), insider threats, and in formulating attack plans until damage has been caused. This study seeks to bridge the gap by investigating how observability tools, like AppDynamics, can be combined with AI algorithms to enable early detection and prevention of cybersecurity threats. The study investigates real-time anomaly detection, predictive threat intelligence, and automated response features to boost security operations and response times. Through the utilization of performance monitoring, behavioral analytics, and machine learning technologies, this study proposes a holistic solution to boost the cybersecurity defenses. This study adds to the growing literature on the convergence of AI technologies and observability, offering practical suggestions for financial institutions seeking to upgrade their cybersecurity systems against increasingly sophisticated attacks.