Lillian Tsai
Lily works as a researcher and engineer at SystemsResearch@Google (SRG), currently investigating frameworks for better security and privacy in agentic systems! In 2024, she graduated with her PhD at MIT in the PDOS group, where her thesis research aimed to design systems for better data protections and security in web applications. She is also broadly interested in multicore performance and scalability, and the application of formal methods in systems.
Besides research, Lily loves playing violin, reading, hiking, climbing, and exploring the world around her.
Research Areas
Authored Publications
Sort By
Preview abstract
Judging an action’s safety requires knowledge of the context in which the action takes place. To human agents who act in various contexts, this may seem obvious: performing an action such as email deletion may or may not be appropriate depending on the email’s content, the goal (e.g., to erase sensitive emails or to clean up trash), and the type of email address (e.g., work or personal). Unlike people, computational systems have often had only limited agency in limited contexts. Thus, manually crafted policies and user confirmation (e.g., smartphone app permissions or network access control lists), while imperfect, have sufficed to restrict harmful actions. However, with the upcoming deployment of generalist agents that support a multitude of tasks (e.g., an automated personal assistant), we argue that we must rethink security designs to adapt to the scale of contexts and capabilities of these systems. As a first step, this paper explores contextual security in the domain of agents and proposes contextual agent security (Conseca), a framework to generate just-in-time, contextual, and human-verifiable security policies.
View details
