PeopleofSuperintelligence

Researcher

Olivia McLaughlin

Also known as Olive Franzese-McLaughlin, Olive Franzese

Olivia McLaughlin, who publishes as Olive Franzese-McLaughlin, is a cryptography and machine-learning researcher who builds ways to audit AI systems while keeping their data and parameters confidential. She studied computer science and biology at Reed College, took a master's degree at the University of Maryland, and completed a PhD in applied cryptography at Northwestern University under Xiao Wang. Her Confidential-PROFITT paper on a confidential proof of fair training appeared at ICLR in 2023, and the Alan Turing Institute named her zero-knowledge fairness work a Top 10 Research Highlight of 2022–23. Papers since then cover model abstention, noise sampling for differential privacy, online fairness certificates (OATH, NeurIPS 2025) and verification of private learning. She is a Vector Distinguished Postdoctoral Fellow at the Vector Institute and the University of Toronto, advised by Nicolas Papernot.

Timeline

  1. 2019

    Hypergraph measures for signaling pathways

    She publishes "Hypergraph-based connectivity measures for signaling pathway topologies" in PLoS Computational Biology in 2019, with A Groce, TM Murali and A Ritz. Her bachelor's degree in computer science and biology is from Reed College.

  2. 2021–2022

    ScalpelSig and a Maryland master's

    She earns a master's degree in machine learning and computational biology at the University of Maryland. Her ScalpelSig paper, on designing targeted genomic panels from data to detect activity of mutational signatures, appears at RECOMB in 2021 and in the Journal of Computational Biology in 2022.

  3. 2021

    Zero-knowledge proofs for RAM programs

    Her PhD work in applied cryptography at Northwestern University is advised by Xiao Wang. At ACM CCS in 2021, she coauthors "Constant-overhead zero-knowledge for RAM programs" with Wang and four other authors.

  4. 2022–2023

    Confidential-PROFITT and a Turing highlight

    She coauthors Confidential-PROFITT, a confidential proof of fair training of trees, which earns a Notable Top 5% Commendation at ICLR in 2023. The Alan Turing Institute recognizes her zero-knowledge work on fairness verification as a Top 10 Research Highlight of 2022–23.

  5. 2023

    Serverless collaborative learning

    She is first author of "Robust and actively secure serverless collaborative learning," published at NeurIPS in 2023. Adam Dziedzic, Nicolas Papernot and Xiao Wang are among the coauthors.

  6. 2025

    OATH, Confidential Guardian and noise sampling

    In 2025, she coauthors Confidential Guardian at ICML, a framework against the abuse of model abstention built on zero-knowledge proofs of verified inference, and Secure Noise Sampling for Differentially Private Collaborative Learning at ACM CCS. She is first author of OATH, a zero-knowledge proof protocol for confidential online group fairness certification, and presents it at NeurIPS in San Diego in December 2025.

  7. 2026

    Verifying private ML at ICML

    In 2026, she coauthors "Efficient Public Verification of Private ML via Regularization" with Zoë Ruha Bell, Anvith Thudi, Nicolas Papernot and Shafi Goldwasser for ICML. It presents a differentially private algorithm with near-optimal privacy-utility trade-offs whose privacy guarantee can be verified with less compute than training. In April 2026, she gives invited talks on cryptographic model certification at colleges including Smith, Wellesley and Williams.

  8. As of October 2026

    Vector postdoctoral fellow in Toronto

    She is a Vector Distinguished Postdoctoral Fellow at the Vector Institute and the University of Toronto, advised by Nicolas Papernot. Her research centers on auditing ML models with cryptography so that sensitive information stays confidential. She comes to Vector from a visiting professorship at Reed College.

Career

  1. NowVector InstituteVector Distinguished Postdoctoral Fellow
  2. NowUniversity of TorontoVector Distinguished Postdoctoral Fellow
  3. Reed CollegeVisiting Professor

Education

  1. 2022University of MarylandMaster's degree
  2. Reed CollegeBachelor's degree
  3. Northwestern UniversityPhD

From the biography.

  1. The median h-index is 48 at universities and 14 at frontier AI labsIncludes University of Toronto. The median h-index is 48 at universities and 14 at frontier AI labs. We compare publishing careers, recent citations, dual appointments and job moves across 2,420 university researchers and 308 frontier-lab researchers.
  2. Of 943 people shaping AI who worked at Google, 446 work there nowIncludes Vector Institute. Our estimates of where the 943 people shaping AI who worked at Google and Google DeepMind work now: 446 at Google and 452 across 278 other organizations.
  3. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes University of Toronto. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.
  4. 84% of people shaping AI with recorded undergraduate and doctoral schools changed institutions for their doctorateIncludes University of Toronto. 84% of people shaping AI with recorded undergraduate and doctoral schools changed institutions for their doctorate. Across 2,116 people with both an undergraduate degree and a doctorate recorded, we trace which undergraduate schools feed which doctoral programs, how often students stay at the same school, and how paths differ by birth-country region.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Olivia McLaughlin yet. Send us a free-licensed photo.

  1. Olivia McLaughlin - Vector Institute for Artificial Intelligence vectorinstitute.ai. Checked 22 October 2026.
  2. Olive Franzese-McLaughlin - Distinguished Postdoctoral Fellow olive-franzese.github.io. Checked 22 October 2026.
  3. CleverHans Lab - Olive cleverhans.io. Checked 22 October 2026.
  4. [2410.02777] Secure and Confidential Certificates of Online Fairness arxiv.org. Checked 22 October 2026.
  5. Secure Noise Sampling for Differentially Private Collaborative Learning eprint.iacr.org. Checked 22 October 2026.
  6. Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention proceedings.mlr.press. Checked 22 October 2026.
  7. [2512.04008] Efficient Public Verification of Private ML via Regularization arxiv.org. Checked 22 October 2026.