I am an Assistant Professor of Computer Science specializing in AI security, adversarial machine learning, and trustworthy artificial intelligence. My research focuses on detecting and mitigating vulnerabilities in modern AI systems, including synthetic and manipulated digital content. I combine machine learning, cybersecurity, and data privacy techniques to develop robust and reliable AI technologies. My work has been published in leading venues across artificial intelligence and security, and I am committed to advancing interdisciplinary research while mentoring students and contributing to the broader scientific community.