New Algorithmic Tools for Rigorous Machine Learning Security Analysis

Event Date: March 4, 2024
Location: 10:30 am
Contact Name: LWSN 3102
Priority: No
School or Program: Electrical and Computer Engineering
College Calendar: Hide
Teodora Baluta
National University of Singapore


Machine learning security is an emerging area with many open questions lacking systematic analysis. In this talk, I will present three new algorithmic tools to address this gap: (1) algebraic proofs; (2) causal reasoning; and (3) sound statistical verification. Algebraic proofs provide the first conceptual mechanism to resolve intellectual property disputes over training data. I show that stochastic gradient descent, the de-facto training procedure for modern neural networks, is a collision-resistant computation under precise definitions. These results open up connections to lattices, which are mathematical tools used for cryptography presently. I will also briefly mention my efforts to analyze causes of empirical privacy attacks and defenses using causal models, and to devise statistical verification procedures with ‘probably approximately correct’ (PAC)-style soundness guarantees.  


Teodora Baluta is a Ph.D. candidate in Computer Science at the National University of Singapore. She enjoys working on security problems that are both algorithmic in nature and practically relevant. She is one of the EECS Rising Stars 2023, a Google PhD Fellow, a Dean’s Graduate Research Excellence Award recipient and a President’s Graduate Fellowship recipient at NUS. She interned at Google Brain working in the Learning for Code team. Her works are published in security (CCS, NDSS), programming languages/verification conferences (OOPSLA, SAT), and software engineering conferences (ICSE, ESEC/FSE). More details are available on her webpage:


Charlie Hu, 

2024-03-04 08:00:00 2024-03-04 17:00:00 America/Indiana/Indianapolis New Algorithmic Tools for Rigorous Machine Learning Security Analysis Teodora Baluta National University of Singapore 10:30 am