General Information
Details
Professor Baluta's research is on rigorous security analysis in (ML) systems. Professor Baluta's approach is to design algorithmic tools with provable guarantees for security analyses and defenses, and show their utility in addressing practical concerns in ML security.
Professor Baluta's teaching is focused in computer security at the undergraduate and graduate level, including cryptography, systems security and network security, as well as machine learning security and privacy. Professor Baluta's research is student-focused and actively involves both graduate and undergraduate students.
[11] Nikolic, Ivica, Teodora Baluta, and Prateek Saxena (2025a). “Model Provenance Testing for Large Language Models”. Advances in Neural Information Processing Systems 38 (NeurIPS).
[10] Baluta, Teodora, Ivica Nikolic, Racchit Jain, Divesh Aggarwal, and Prateek Saxena (2023a). “Unforgeability in Stochastic Gradient Descent”. Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security (CCS).
[9] Wang, Bo, Aashish Kolluri, Ivica Nikolic, Teodora Baluta, and Prateek Saxena (2023). “User-customizable Transpilation of Scripting Languages”. ACM SIGPLAN International Conference on Object-oriented programming systems, languages, and applications (OOPSLA).
[8] Yang, Jiong, Arijit Shaw, Teodora Baluta, Mate Soos, and Kuldeep S. Meel (2023). “Explaining SAT Solving Using Causal Reasoning”. Proceedings of International Conference on Theory and Applications of Satisfiability Testing (SAT).
[7] Baluta, Teodora, Shiqi Shen, S Hitarth, Shruti Tople, and Prateek Saxena (2022b). “Membership Inference Attacks and Generalization: A Causal Perspective”. Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security (CCS).
[6] Kolluri, Aashish, Teodora Baluta, Bryan Hooi, and Prateek Saxena (2022). “LPGNet: Link Private Graph Networks for Node Classification”. Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security (CCS).
[5] Baluta, Teodora, Zheng Leong Chua, Kuldeep S Meel, and Prateek Saxena (2021a). “Scalable Quantitative Verification For Deep Neural Networks”. Proceedings of the 43rd International Conference on Software Engineering (ICSE).
[4] Kolluri, Aashish, Teodora Baluta, and Prateek Saxena (2021). “Private hierarchical clustering in federated networks”. Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security (CCS).
[3] Wang, Bo, Teodora Baluta, Aashish Kolluri, and Prateek Saxena (2021). “SynGuar: guaranteeing generalization in programming by example”. Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE).
[2] Baluta, Teodora, Shiqi Shen, Shweta Shinde, Kuldeep S Meel, and Prateek Saxena (2019a). “Quantitative verification of neural networks and its security applications”. Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security (CCS).
[1] Chua, Zheng Leong, Yanhao Wang, Teodora Baluta, Prateek Saxena, Zhenkai Liang, and Purui Su (2019). “One Engine To Serve’em All: Inferring Taint Rules Without Architectural Semantics”. Proceedings of the Symposium on Network and Distributed System Security (NDSS).