My research centers on enhancing the security and trustworthiness of AI agents, which are rapidly becoming integral to modern digital ecosystems across industries. As their adoption accelerates, these agents face emerging cybersecurity threats including prompt injection, jailbreak exploits, and adversarial attacks that can compromise their integrity and reliability. I investigate robust mitigation strategies to safeguard AI systems against such vulnerabilities, with the ultimate goal of delivering resilient and trustworthy AI solutions for end users in sectors such as government, enterprise, and civil society.
