Marika Swanberg

I am a Research Scientist on Pritish Kamath's team in NYC. Before joining Google Research, I worked on AI agent safety in Chrome. I graduated with my PhD from Boston University, advised by Adam Smith. I am generally interested in real-world deployments of differential privacy (DP) and threat modeling for real systems. Previously, I've dabbled in cryptography, theory of DP, and their connections to legal questions.
Authored Publications
Sort By
  • Title
  • Title, descending
  • Year
  • Year, descending
Preview abstract We study differentially private k-mean/median clustering in the online streaming setting where a point arrive at each time step and we need to output a set of k centers that optimize the k-mean/median objective of all the points so far. We give a generic transformation that turns the sensitive stream into a differentially private stream, which is a semi-coreset of the original stream and allows us to run any (non-private) online clustering algorithm as a post-processing step. Our algorithm is efficient in terms of errors, space and running time compared to existing algorithms (Epasto et al., 2023; Dupr{\'{e}} la Tour, 2024). Furthermore, our reduction allows us to inherit properties of the non-private clustering, such as consistency (Lattanzi and Vassilvitski, 2017), which was not satisfied by previous DP algorithms. View details
Extractable Memorization from First Principles
A. Feder Cooper
Jamie Hayes
Lea Duesterwald
Christopher De Sa
Georgios Kaissis
Daniel E. Ho
Mark A. Lemley
Percy Liang
2026
Preview abstract Recent studies on large language models (LLMs) frequently make broad claims regarding privacy harms and copyright infringement based on supposedly "extracted" training data. However, many of these extraction procedures are imprecise because they fail to distinguish between true memorization and the model's general predictive capabilities. We establish a formal framework for extractable memorization from first principles. We demonstrate that all valid extraction procedures must be grounded in a conformal test that calibrates memorization claims by comparing the generation probabilities of candidate training sequences against matched non-member controls. By establishing a calibrated threshold that controls the false-positive rate, our framework reveals why some existing extraction claims are statistically invalid, particularly for short sequences where verbatim generation of non-training data is common. This rigorous definition is essential for accurately evaluating and communicating the legal and privacy risks of LLMs. View details
Preview abstract Differentially private (DP) synthetic data is a versatile tool for enabling the analysis of private data. With the rise of foundation models, a number of new synthetic data algorithms privately finetune the weights of foundation models to improve over existing approaches to generating private synthetic data. In this work, we propose two algorithms for using API access only to generate DP tabular synthetic data. We extend the Private Evolution algorithm \citep{lin2023differentially, xie2024differentially} to the tabular data domain, define a workload-based distance measure, and propose a family of algorithms that use one-shot API access to LLMs. View details
Preview abstract Differentially private (DP) synthetic data is a versatile tool for enabling the analysis of private data. Recent advancements in large language models (LLMs) have inspired a number of algorithm techniques for improving DP synthetic data generation. One family of approaches uses DP finetuning on the foundation model weights; however, the model weights for state-of-the-art models may not be public. In this work we propose two DP synthetic tabular data algorithms that only require API access to the foundation model. We adapt the Private Evolution algorithm (Lin et al., 2023; Xie et al., 2024) -- which was designed for image and text data -- to the tabular data domain. In our extension of Private Evolution, we define a query workload-based distance measure, which may be of independent interest. We propose a family of algorithms that use one-shot API access to LLMs, rather than adaptive queries to the LLM. Our findings reveal that API-access to powerful LLMs does not always improve the quality of DP synthetic data compared to established baselines that operate without such access. We provide insights into the underlying reasons and propose improvements to LLMs that could make them more effective for this application. View details
Preview abstract Differentially private (DP) synthetic data is a versatile tool for enabling the analysis of private data. With the rise of foundation models, a number of new synthetic data algorithms privately finetune the weights of foundation models to improve over existing approaches to generating private synthetic data. In this work, we propose two algorithms for using API access only to generate DP tabular synthetic data. We extend the Private Evolution algorithm \citep{lin2023differentially, xie2024differentially} to the tabular data domain, define a workload-based distance measure, and propose a family of algorithms that use one-shot API access to LLMs. View details
×