About

I am a fourth-year PhD student at Stanford University, advised by Prof. Sanmi Koyejo in the STAIR Lab. Prior to my PhD, I completed my Master’s degree in Computer Science at University of Toronto under supervision by Prof. Nicolas Papernot in the CleverHans Lab and Prof. Marzyeh Ghassemi in the HealthyML lab. Previously, I received my B.S. in Mathematics from University of Southern California, with minors in Chemistry and Computer Science.

Through the past several years, my research interests have spanned causality; statistical learning theory; representation learning; optimization; algorithmic fairness and equity in machine learning; differential privacy; and generalizable applications of machine learning in the healthcare and biological domains. I continue to be motivated by a broad range of topics and research questions under the general umbrella of mathematics and statistical learning.

Publications

Unell, A.*, Dullerud, N.*, Shah, N., Koyejo, S. (2025). Smarter Sampling for LLM Judges: Reliable Evaluation on a Budget. LLM Evaluation Workshop at the 39th Conference on Neural Information Processing Systems (NeurIPS).

Yaghini, M., Liu, P., Magnuson, A., Dullerud, N., Papernot, N. (2025). Trustworthy ML Regulation as a Principal-Agent Problem. Proceedings of the 8th ACM Conference on Fairness, Accountability, and Transparency (FAccT).

Fang, C., Jia, H., Thudi, A., Yaghini, M., Choquette-Choo, C. A., Dullerud, N., Chandrasekaran, V., Papernot, N. (2023). Proof-of-learning is currently more broken than you think. Proceedings of the 8th IEEE European Symposium on Security and Privacy (EuroS&P).

Shamsabadi, A. S.*, Yaghini, M.*, Dullerud, N.*, Wyllie, S., Aïvodji, U., Alaagib, A., Gambs, S., Papernot, N. (2022) Washing The Unwashable: On the (Im)possibility of Fairwashing Detection. Proceedings of the 36th Conference on Neural Information Processing Systems (NeurIPS).

Dullerud, N., Roth, K., Hamidieh, K., Papernot, N., Ghassemi, M. (2022). Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning. Proceedings of the 10th International Conference on Learning Representations (ICLR).

** Banerjee, I., Bhimireddy, A. R., Burns, J. L., Celi, L. A., Chen, L., Correa, R., Dullerud, N., Ghassemi, M., Gichoya, J.W., Huang, S., Kuo, P., Lungren, M. P., Price, B. J., Purkayastha, S., Pyrros, A. A., Oakden-Rayner, L., Okechukwu, C., Seyyed-Kalantari, L., Trivedi, H., Wang, R., Zaiman, Z., Zhang, H. (2022). Reading Race: AI Recognizes Patient’s Racial Identity In Medical Images. The Lancet Digital Health.

Zhang, H., Dullerud, N., Seyyed-Kalantari, L., Morris, Q., Joshi, S., Ghassemi, M. (2021). An Empirical Framework for Domain Generalization in Clinical Settings. Proceedings of the 2nd ACM Conference on Health, Inference, and Learning (CHIL).

Jia, H.*, Yaghini, M.*, Choquette-Choo, C.A.†, Dullerud, N.†, Thudi, A.†, Chandrasekaran, V., Papernot, N. (2021). Proof-of-Learning: Definitions and Practice. Proceedings of the 42nd IEEE Symposium on Security and Privacy (S&P).

Cheng, V., Suriyakumar, V., Dullerud, N., Joshi, S., Ghassemi, M. (2021). Can You Fake It Until You Make It?: Impacts of Differentially Private Synthetic Data on Downstream Classification Fairness. Proceedings of the 4th ACM Conference on Fairness, Accountability, and Transparency (FAccT).

Choquette-Choo, C.A.*, Dullerud, N.*, Dziedzic, A.*, Zhang, Y.*, Jha, S., Wang, X., Papernot, N. (2021). CaPC Learning: Confidential and Private Collaborative Learning. Proceedings of the 9th International Conference on Learning Representations (ICLR).

Brown, C. E., Alizadeh, D., Jonsson, V. D., Hibbard, J., Yahn, S., Wong, R. A., Yang, X., Ng, R., Dullerud, N., Maker, M., Gholamin, S., Starr, R.,Banovich, N., Forman, S. J., Badie, B. (2021). CAR T cell therapy reshapes the tumor microenvironment to promote host antitumor immune repsonses in glioblastoma. Cancer Research, 81(13), 59-59.

Dullerud, N., Freedman-Susskind, T., Gnanapragasam, P., Snow, C., West, A.P., and Jonsson, V.D. (2020). Feature selection and combinatorial optimization on fitness landscapes to constrain anti-SARS-CoV2 antibody design and address viral escape. Learning Meaningful Representations of Life (LMRL) Workshop at the 34th Conference on Neural Information Processing Systems (NeurIPS).

Dullerud, N., Jonsson, V.D. (2020). Cellular Immunotherapy Treatment Scheduling to Address Antigen Escape. Proceedings of the 59th IEEE Conference on Decision and Control (CDC).

*, † Equal author contribution, authors listed alphabetically by name
** All authors listed alphabetically

Pre-prints

Chen, E., Truong, S. T., Dullerud, N., Koyejo, S., & Guestrin, C. (2025). Interactive Multi-Objective Probabilistic Preference Learning with Soft and Hard Bounds. arXiv preprint arXiv:2506.21887.

Chen, E., Dullerud, N., Niedermayr, T., Kidd, E., Senanayake, R., Koh, P. W., Koyejo, S., Guestrin, C. (2024). MoSH: Modeling Multi-Objective Tradeoffs with Soft and Hard Bounds. arXiv preprint arXiv:2412.06154.

Jonsson, V. D., Ng, R. H., Dullerud, N., Wong, R. A., Hibbard, J., Wang, D., Aguilar, B., Starr, R., Weng, L., Alizadeh, D., Forman, S. J., Badie, B., Brown, C. E. (2021). CAR T cell therapy drives endogenous locoregional T cell dynamics in a responding patient with glioblastoma. BioRxiv preprint.

Recorded Presentations

Fairness in representation learning—A study in evaluation and mitigation of bias in deep metric learning, MedAI Stanford, Virtual, 2022

CaPC—Confidential and Private Collaborative Learning, AI Superstream Series: Securing AI, O’Reilly Media Sponsored by Intel, Virtual, 2021

Proof-Of-Learning: Definitions and Practice, Proceedings of the 42nd IEEE Symposium on Security and Privacy, Virtual, 2021

Blog Posts

Here are some blog posts which I have co-authored:

Contact

The best way to reach me is via email: natalie [dot] dullerud [at] stanford [dot] edu