Teodora Baluta

Security & Privacy | Machine Learning | Formal Guarantees


I’m a Ph.D candidate at School of Computing, National University of Singapore (NUS), advised by Prateek Saxena and Kuldeep S. Meel. I am a part of the KISP lab, as well as MeelGroup.

I work in computer security. I aim to build Foundations for Machine Learning (ML) Security. To this end, my research has proposed:

  1. Refutable bases for attacks that refine the ML security definitions: causal reasoning for analyzing membership inference attacks [CCS 22a]; and
  2. Statistical verifiability techniques for ML systems: black-box [ICSE 21] and white-box quantitative verification for neural nets [CCS 19] that combine probabilistic analysis with logic. I enjoy algorithmic approaches, and have collaborated on building private learning for graph data [CCS 21][CCS 22b].

Beyond my main research focus, I am excited about combining statistical and symbolic techniques to enable generalizable and explainable symbolic systems, and I have collaborated towards Learnability of Analysis Rules [OOPSLA 23][FSE 21][NDSS 19][SAT 23].

My research has been recognized and supported by the Google PhD Fellowship (2021-2023), Dean’s Graduate Research Excellence Award (2022-2023, Sem.2), and the President’s Graduate Fellowship (2017-2021). I was selected as a finalist for the Microsoft Research PhD Fellowship, Asia-Pacific (2021).

I enjoy teaching, and I was fortunate to be a Teaching Assistant @ NUS for several courses: Systems Security CS5231 Fall 2019, Systems Security CS5231 Fall 2018, Intro to Security CS3235.


Sep 3, 2023 Our paper Unforgeability in Stochastic Gradient Descent has been accepted at CCS 2023! Joint work with Ivica Nikolic, Racchit Jain, Divesh Aggarwal, and Prateek Saxena.
Aug 11, 2023 I am happy to announce that I received the Dean’s Graduate Research Excellence Award from the School of Computing, NUS for my research!
May 16, 2023 Our paper Explaining SAT Solving Using Causal Reasoning has been accepted at SAT 2023! Joint work with Jiong Yang, Arijit Shaw, Mate Soos, and Kuldeep S. Meel.
Mar 8, 2023 Gave a talk at Women in Tech - DigitALL @ SoC. Happy Women’s Day!
Feb 24, 2023 Gave a talk on “Hardness of Testing Machine Learning” at Research Week.