About Me
I work as a researcher and engineer at SystemsResearch@Google (SRG), currently investigating frameworks for better security and privacy in agentic systems! In 2024, I graduated with my PhD at MIT in the PDOS group, where my thesis research aimed to design systems for better data protections and security in web applications. I am also broadly interested in multicore performance and scalability, and the application of formal methods in systems.
Besides research, I love playing violin, reading, hiking, climbing, and exploring the world around me. I am always free to sightread chamber music!
History
- 2024-Present: Working as a Systems Research Engineer at SystemsResearch@Google (SRG)!
- 2018-2024: PhD student in PDOS at MIT, advised by Frans Kaashoek and Malte Schwarzkopf.
- 2023: Student Researcher at SRG with Anastasia Ailamaki, Kim Keeton, and Philip Levis.
- 2019: Research Intern at MSR, working with Stefan Saroiu and Alec Wolman.
- 2017-18: Fulbright Research Fellow at MPI-SWS in Germany, advised by Prof. Peter Druschel.
- 2013-17: Got my Bachelor's/Master's degrees in Computer Science at Harvard, advised by Prof. Eddie Kohler.
- Pre-2013: Grew up in the sunny California Bay Area!
Publications
ContinuousBench: Can Differentially Private Synthetic Text Improve Capabilities? (TPDP 2026)
Peihan Liu,
Lucas Rosenblatt,
Weiwei Kong,
Natalia Ponomareva,
Gautam Kamath,
Rachel Cummings,
Roxana Geambasu,
Yu Gan,
Lillian Tsai,
Alex Bie
Engineering Robustness into Personal Agents with the AI Workflow Store (under submission)
Roxana Geambasu,
Mariana Raykova,
Pierre Tholoniat,
Trishita Tiwari,
Lillian Tsai,
Wen Zhang
An AI Agent Execution Environment to Safeguard User Data (under submission)
Robert Stanley,
Avi Verma,
Lillian Tsai,
Konstantinos Kallas,
Sam Kumar
IC-Cache: Efficient Large Language Model Serving via In-context Caching (SOSP 2025)
Yifan Yu,
Yu Gan,
Nikhil Sarda,
Lillian Tsai,
Jiaming Shen,
Yanqi Zhou,
Arvind Krishnamurthy,
Fan Lai,
Henry M. Levy,
David Culler
Contextual Agent Security: A Policy for Every Purpose (HotOS 2025)
Lillian Tsai,
Eugene Bagdasarian
Flexible Privacy via Disguising and Revealing (MIT PhD Thesis)
Lillian Tsai
Edna: Disguising and Revealing User Data in Web Applications (SOSP 2023)
Lillian Tsai,
Hannah Gross,
Frans Kaashoek,
Eddie Kohler,
Malte Schwarzkopf
Privacy Heroes Need Data Disguises (HotOS 2021)
Best presentation runner-up
Lillian Tsai,
Malte Schwarzkopf,
Eddie Kohler
CaSA: End-to-end Quantitative Security Analysis of Randomly Mapped Caches (MICRO 2020)
Intel Hardware Security Academic Award Finalist
Thomas Bourgeat,
Jules Drean,
Yuheng Yang,
Lillian Tsai,
Joel Emer,
Mengjia Yan
Are We Susceptible to Rowhammer? An End-to-End Methodology for Cloud Providers (IEEE S&P 2020)
Lucian Cojocar,
Jeremie Kim,
Minesh Patel,
Lillian Tsai,
Stefan Saroiu,
Alec Wolman,
Onur Mutlu
enClosure: Group Communication via Encounter Closures (MobiSys 2019)
Lillian Tsai,
Roberta De Viti,
Matthew Lentz,
Stefan Saroiu,
Bobby Bhattacharjee,
Peter Druschel
A Revised and Verified Proof of the Scalable Commutativity Rule (arXiv 2018)
Lillian Tsai,
Eddie Kohler,
Frans Kaashoek,
Nickolai Zeldovich
Concurrent Algorithms in Transactional Data Structures (Harvard Thesis)
Lillian Tsai
Type Aware Transactions for Faster Concurrent Code (Eurosys 2016)
Nathaniel Herman,
Jeevana Inala,
Yihe Huang,
Lillian Tsai,
Eddie Kohler,
Barbara Liskov,
Liuba Shrira
Invited Public Talks
- Security Agentic AI: Contextual Security and Beyond
- Brown Systems Week Keynote (June 14, 2026)
- UCLA Systems Seminar (May 13, 2026)
- Berkeley Security Seminar (May 6, 2026)
- Tools for Thought: Building Reliable AI Agents with Preferences and Context -- Brown University Lecture with Serena Booth (April 16, 2026)
Flexible Privacy via Disguising and Revealing -- Berkeley NetSys Talks (Nov 9, 2023)
