Lydia Zakynthinou

Lydia Zakynthinou is an Assistant Professor in the Department of Computer Science at Johns Hopkins University and a member of the Johns Hopkins Data Science and AI Institute. Her research centers on theoretical foundations of trustworthy machine learning, focusing on privacy-preserving methods with formal guarantees and exploring connections between privacy, robustness, and generalization.

Education:

• PhD in Computer Science, Northeastern University (advised by Jonathan Ullman and Huy Lê Nguyễn)
• MSc in Logic, Algorithms, and Theory of Computation, National Kapodistrian University of Athens
• Diploma in Electrical and Computer Engineering, National Technical University of Athens

Her research spans Data Privacy (particularly differential privacy), Machine Learning Theory, and Responsible Computing. She develops privacy-preserving methods with rigorous theoretical analysis while maintaining practical performance, investigating fundamental limitations and surprising connections to robustness and memorization in learning algorithms. Her work bridges theoretical guarantees with real-world applicability for data practitioners.

Recent publications (2018-2025) demonstrate consistent focus on differential privacy in high-dimensional statistics, private mean estimation, and robustness-privacy tradeoffs. She has published in top venues including NeurIPS, ICML, and COLT, with multiple spotlight presentations recognizing significant contributions to private machine learning theory.

Scientific Awards:

• Meta Research PhD Fellowship (2020)
• Northeastern University Khoury College PhD Research Award (2022)
• Foundations of Data Science Institute postdoctoral fellowship
• Northeastern University Dissertation Fellowship (2023)

Dr. Zakynthinou actively contributes to the academic community through program committee service for IEEE S&P, ICML, NeurIPS (Technical and Ethics Reviewer), TPDP, AAAI, FAccT, and COLT. She organizes the Boston-area Differential Privacy Seminar and NEU Theory Seminar, and co-founded the Khoury PhD Women Group. Her research has been supported by prestigious fellowships including Meta Research and FODSI.

As a member of the Johns Hopkins Data Science and AI Institute and Learning Theory Alliance workshop committee, she holds weekly office hours and organizes community events including fireside chats with leading researchers and mentorship roundtables for early-career scholars.