0009-0004-2344-4840 About
I am a Cloud Security Engineer and AI Security Researcher at Google.
My research focuses on the security of Generative AI systems, particularly in defending against prompt injection, multi-turn adversarial attacks, and coordination vulnerabilities in Agentic frameworks.
I have authored work on large language model (LLM) security, differential privacy, and federated learning, and I’m passionate about building trustworthy AI systems. In addition, I’m developing tools and best practices for securing AI pipelines in both enterprise and academic settings.
My long-term goal is to advance safe, explainable, and secure AI for mission-critical applications.
Employment
-
Google (United States) Lead AI Security Research Engineer
Education
-
University of Chicago Masters of Science2023 - 2025
Projects & Funding
Projects & funding information is unavailable.
Publications (5)
- Temporal Context Awareness: A Defense Framework Against Multi-Turn Manipulation Attacks on Large Language Models Save
- Official Google Cloud Certified Professional Cloud Security Engineer Exam Guide: Save
- Automatically Detecting Expensive Prompts and Configuring Firewall Rules to Mitigate Denial of Service Attacks on Large Language Models Save
- Building A Secure Agentic AI Application Leveraging A2A Protocol Save
- Tenant Data Security for LLM Applications in a Multi-Tenancy Environment Save