Juniper Lovato

Juniper Lovato, Philip Mueller, Parisa Suchdev et al.

Collecting personally identifiable information (PII) on data subjects has become big business. Data brokers and data processors are part of a multi-billion-dollar industry that profits from collecting, buying, and selling consumer data. Yet there is little transparency in the data collection industry which makes it difficult to understand what types of data are being collected, used, and sold, and thus the risk to individual data subjects. In this study, we examine a large textual dataset of privacy policies from 1997-2019 in order to investigate the data collection activities of data brokers and data processors. We also develop an original lexicon of PII-related terms representing PII data types curated from legislative texts. This mesoscale analysis looks at privacy policies overtime on the word, topic, and network levels to understand the stability, complexity, and sensitivity of privacy policies over time. We find that (1) privacy legislation correlates with changes in stability and turbulence of PII data types in privacy policies; (2) the complexity of privacy policies decreases over time and becomes more regularized; (3) sensitivity rises over time and shows spikes that are correlated with events when new privacy legislation is introduced.

Juniper Lovato, Laurent Hébert-Dufresne, Mohsen Ghasemizade et al.

Privacy preferences are not fixed individual traits, they depend on context and lived experiences. In this study, we analyze 2,912 survey responses from 782 college students collected over seven survey periods during 2023 and 2024. We ask about their usage of social media, the security settings of their accounts, and measure their comfort in sharing personally identifiable information (PII) across 17 different institutional contexts. Compared to past research, we observe a large shift towards private accounts, going from 1/3rd private in 2007 to 2/3rds in 2024, and find that participants' discomfort sharing PII with social media platforms strongly predicts their privacy settings. Beyond social media, we identify a stable ranking of institutional trust, though some institutions, like the police, show high variability reflecting divergent lived experiences. Traditionally marginalized groups and participants having faced adverse childhood experiences show more discomfort with institutions of power, especially in areas where they face greater vulnerability. We argue for context-adaptive privacy settings that recognize institutional relationships and demographic vulnerabilities, moving beyond one-size-fits-all consent frameworks toward contextually appropriate data governance.

Aviral Chawla, Galen Hall, Juniper Lovato

Foundation models must handle multiple generative processes, yet mechanistic interpretability largely studies capabilities in isolation; it remains unclear how a single transformer organizes multiple, potentially conflicting "world models". Previous experiments on Othello playing neural-networks test world-model learning but focus on a single game with a single set of rules. We introduce MetaOthello, a controlled suite of Othello variants with shared syntax but different rules or tokenizations, and train small GPTs on mixed-variant data to study how multiple world models are organized in a shared representation space. We find that transformers trained on mixed-game data do not partition their capacity into isolated sub-models; instead, they converge on a mostly shared board-state representation that transfers causally across variants. Linear probes trained on one variant can intervene on another's internal state with effectiveness approaching that of matched probes. For isomorphic games with token remapping, representations are equivalent up to a single orthogonal rotation that generalizes across layers. When rules partially overlap, early layers maintain game-agnostic representations while a middle layer identifies game identity, and later layers specialize. MetaOthello offers a path toward understanding not just whether transformers learn world models, but how they organize many at once.

Mohsen Ghasemizade, Juniper Lovato, Christopher M. Danforth et al.

Sharing health and behavioral data raises significant privacy concerns, as conventional de-identification methods are susceptible to privacy attacks. Differential Privacy (DP) provides formal guarantees against re-identification risks, but practical implementation necessitates balancing privacy protection and the utility of data. We demonstrate the use of DP to protect individuals in a real behavioral health study, while making the data publicly available and retaining high utility for downstream users of the data. We use the Adaptive Iterative Mechanism (AIM) to generate DP synthetic data for Phase 1 of the Lived Experiences Measured Using Rings Study (LEMURS). The LEMURS dataset comprises physiological measurements from wearable devices (Oura rings) and self-reported survey data from first-year college students. We evaluate the synthetic datasets across a range of privacy budgets, epsilon = 1 to 100, focusing on the trade-off between privacy and utility. We evaluate the utility of the synthetic data using a framework informed by actual uses of the LEMURS dataset. Our evaluation identifies the trade-off between privacy and utility across synthetic datasets generated with different privacy budgets. We find that synthetic data sets with epsilon = 5 preserve adequate predictive utility while significantly mitigating privacy risks. Our methodology establishes a reproducible framework for evaluating the practical impacts of epsilon on generating private synthetic datasets with numerous attributes and records, contributing to informed decision-making in data sharing practices.