Software systems and applications are designed with many configuration parameters that contribute to various functionalities such as architecture, virtualization, performance, security, privacy, and system interactions. However, software misconfiguration can result in system vulnerabilities and susceptibility to security attacks. The Open Web Application Security Project, a nonprofit foundation, considers security misconfiguration as one of the top risks to cybersecurity. One of the major challenges such software systems face is they are generally built to operate with relatively static configurations over extended periods. This static approach can result in system vulnerabilities that may be exploited by adversaries during the reconnaissance stage, increasing the likelihood of successful attacks. In this talk, Dr. Shuvalaxmi will address the above cybersecurity challenge by applying Machine Learning algorithms to enhance the security and robustness of software systems. She will present a “Reinforcement Learning-based Game Model” to automate the dynamic Moving Target Defense (MTD) strategy for safeguarding vulnerable software from adversarial attacks. Finally, she will conclude her talk with exciting future directions in the field of AI and evolutionary algorithms in cybersecurity. Co-sponsored by: LaRRIS (Laboratoire de Recherche en Réseaux, Informatique et Sécurité) Faculty of Sciences Lebanese Univesity Speaker(s): , Dr. Shuvalaxmi Dass Virtual: https://events.vtools.ieee.org/m/364473