arXiv subjects

Lucas Rosenblatt

Publications and source records attributed to Lucas Rosenblatt.

At least 19 recordsLinked to original sources

arXiv2026

How to DP-fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy

High quality data is needed to unlock the full potential of AI for end users. However finding new sources of such data is getting harder: most publicly-available human generated data will soon have been used. Additionally, publicly available data often is not representative of users of a particular system -- for example, a research speech dataset of contractors interacting with an AI assistant will likely be more homogeneous, well articulated and self-censored than real world commands that end users will issue. Therefore unlocking high-quality data grounded in real user interactions is of vital interest. However, the direct use of user data comes with significant privacy risks. Differential Privacy (DP) is a well established framework for reasoning about and limiting information leakage, and is a gold standard for protecting user privacy. The focus of this work, \emph{Differentially Private Synthetic data}, refers to synthetic data that preserves the overall trends of source data,, while providing strong privacy guarantees to individuals that contributed to the source dataset. DP synthetic data can unlock the value of datasets that have previously been inaccessible due to privacy concerns and can replace the use of sensitive datasets that previously have only had rudimentary protections like ad-hoc rule-based anonymization. In this paper we explore the full suite of techniques surrounding DP synthetic data, the types of privacy protections they offer and the state-of-the-art for various modalities (image, tabular, text and decentralized). We outline all the components needed in a system that generates DP synthetic data, from sensitive data handling and preparation, to tracking the use and empirical privacy testing. We hope that work will result in increased adoption of DP synthetic data, spur additional research and increase trust in DP synthetic data approaches.

cs.CR↗

arXiv2026

ContinuousBench: Can Differentially Private Synthetic Text Improve Capabilities?

Differentially private (DP) text synthesis promises to unlock sensitive corpora for model training, but it remains unclear whether DP synthetic data transmits genuinely new knowledge and capabilities present only in those corpora. This is because existing evaluations rely on tasks that are nearly solvable without training, so strong benchmark performance does not establish that DP synthesis can substitute original data access. Thus, we introduce ContinuousBench, a continuously and automatically-regenerated benchmark that measures capability gain from DP synthetic text. Each quarter, a new release pairs a never-before-seen training corpus with a derived QA set, constructed to be: (1) unsolvable sans-corpus; and (2) learnable under DP, as the tested knowledge is supported by hundreds of independent records. Researchers produce DP synthetic data from the training corpus and run our standardized training and evaluation harness on their synthetic data to measure gains. We instantiate two tracks: Geminon, a procedurally-generated dataset about fictional creatures; and News, a stream of newly crawled public news articles. Although standard benchmarks are nearly saturated, on ContinuousBench we find that non-private synthesis transfers substantial knowledge from the original corpus, while state-of-the-art DP synthesis methods generally fail to do so, even at $\varepsilon=100$.

cs.LG↗

arXiv2026

Sharper Bounds for Chebyshev Moment Matching, with Applications

We study the problem of approximately recovering a probability distribution given noisy measurements of its Chebyshev polynomial moments. This problem arises broadly across algorithms, statistics, and machine learning. By leveraging a global decay bound on the coefficients in the Chebyshev expansion of any Lipschitz function, we sharpen prior work, proving that accurate recovery in the Wasserstein distance is possible with more noise than previously known. Our result immediately yields a number of applications: 1) We give a simple "linear query" algorithm for constructing a differentially private synthetic data distribution with Wasserstein-$1$ error $\tilde{O}(1/n)$ based on a dataset of $n$ points in $[-1,1]$. This bound is optimal up to log factors, and matches a recent result of Boedihardjo, Strohmer, and Vershynin [Probab. Theory. Rel., 2024], which uses a more complex "superregular random walk" method. 2) We give an $\tilde{O}(n^2/ε)$ time algorithm for the linear algebraic problem of estimating the spectral density of an $n\times n$ symmetric matrix up to $ε$ error in the Wasserstein distance. Our result accelerates prior methods from Chen et al. [ICML 2021] and Braverman et al. [STOC 2022]. 3) We tighten an analysis of Vinayak, Kong, Valiant, and Kakade [ICML 2019] on the maximum likelihood estimator for the statistical problem of "Learning Populations of Parameters'', extending the parameter regime in which sample optimal results can be obtained. Beyond these main results, we provide an extension of our bound to estimating distributions in $d > 1$ dimensions. We hope that these bounds will find applications more broadly to problems involving distribution recovery from noisy moment information.

cs.DS↗

arXiv2026

Towards Provably Unbiased LLM Judges via Bias-Bounded Evaluation

As AI models progress beyond simple chatbots into more complex workflows, we draw ever closer to the event horizon beyond which AI systems will be utilized in autonomous, self-maintaining feedback loops. Any autonomous AI system will depend on automated, verifiable rewards and feedback; in settings where ground truth is sparse or non-deterministic, one practical source of such rewards is an LLM-as-a-Judge. Although LLM judges continue to improve, the literature has yet to introduce systems capable of enforcing standards with strong guarantees, particularly when bias vectors are unknown or adversarially discovered. To remedy this issue, we propose average bias-boundedness (A-BB), an algorithmic framework which formally guarantees reductions of harm/impact as a result of any measurable bias in an LLM judge. Evaluating on Arena-Hard-Auto with four LLM judges, we achieve (tau=0.5, delta=0.01) bias-bounded guarantees while retaining 61-99% correlation with original rankings across formatting and schematic bias settings, with most judge-bias combinations exceeding 80%. The code to reproduce our findings is available at https://github.com/penfever/bias-bounded-evaluation.

cs.AI↗

arXiv2026

Exactly Computing do-Shapley Values

Structural Causal Models (SCM) are a powerful framework for describing complicated dynamics across the natural sciences. A particularly elegant way of interpreting SCMs is do-Shapley, a game-theoretic method of quantifying the average effect of $d$ variables across exponentially many interventions. Like Shapley values, computing do-Shapley values generally requires evaluating exponentially many terms. The foundation of our work is a reformulation of do-Shapley values in terms of the irreducible sets of the underlying SCM. Leveraging this insight, we can exactly compute do-Shapley values in time linear in the number of irreducible sets $r$, which itself can range from $d$ to $2^d$ depending on the graph structure of the SCM. Since $r$ is unknown a priori, we complement the exact algorithm with an estimator that, like general Shapley value estimators, can be run with any query budget. As the query budget approaches $r$, our estimators can produce more accurate estimates than prior methods by several orders of magnitude, and, when the budget reaches $r$, return the Shapley values up to machine precision. Beyond computational speed, we also reduce the identification burden: we prove that non-parametric identifiability of do-Shapley values requires only the identification of interventional effects for the $d$ singleton coalitions, rather than all classes.

cs.LG↗

arXiv2026

Privately Fine-Tuned LLMs Preserve Temporal Dynamics in Tabular Data

Research on differentially private synthetic tabular data has largely focused on independent and identically distributed rows where each record corresponds to a unique individual. This perspective neglects the temporal complexity in longitudinal datasets, such as electronic health records, where a user contributes an entire (sub) table of sequential events. While practitioners might attempt to model such data by flattening user histories into high-dimensional vectors for use with standard marginal-based mechanisms, we demonstrate that this strategy is insufficient. Flattening fails to preserve temporal coherence even when it maintains valid marginal distributions. We introduce PATH, a novel generative framework that treats the full table as the unit of synthesis and leverages the autoregressive capabilities of privately fine-tuned large language models. Extensive evaluations show that PATH effectively captures long-range dependencies that traditional methods miss. Empirically, our method reduces the distributional distance to real trajectories by over 60% and reduces state transition errors by nearly 50% compared to leading marginal mechanisms while achieving similar marginal fidelity.

cs.LG↗

arXiv2026

Explanation Multiplicity in SHAP: Characterization and Assessment

Post-hoc explanations are widely used to justify, contest, and review automated decisions in high-stakes domains such as lending, employment, and healthcare. Among these methods, SHAP is often treated as providing a reliable account of which features mattered for an individual prediction and is routinely used to support recourse, oversight, and accountability. In practice, however, SHAP explanations can differ substantially across repeated runs, even when the individual, prediction task, and trained model are held fixed. We conceptualize and name this phenomenon explanation multiplicity: the existence of multiple, internally valid but substantively different explanations for the same decision. Explanation multiplicity poses a normative challenge for responsible AI deployment, as it undermines expectations that explanations can reliably identify the reasons for an adverse outcome. We present a comprehensive methodology for characterizing explanation multiplicity in post-hoc feature attribution methods, disentangling sources arising from model training and selection versus stochasticity intrinsic to the explanation pipeline. Furthermore, whether explanation multiplicity is surfaced depends on how explanation consistency is measured. Commonly used magnitude-based metrics can suggest stability while masking substantial instability in the identity and ordering of top-ranked features. To contextualize observed instability, we derive and estimate randomized baseline values under plausible null models, providing a principled reference point for interpreting explanation disagreement. Across datasets, model classes, and confidence regimes, we find that explanation multiplicity is widespread and persists even under highly controlled conditions, including high-confidence predictions. Thus explanation practices must be evaluated using metrics and baselines aligned with their intended societal role.

cs.LG↗

arXiv2025

SimKey: A Semantically Aware Key Module for Watermarking Language Models

The rapid spread of text generated by large language models (LLMs) makes it increasingly difficult to distinguish authentic human writing from machine output. Watermarking offers a promising solution: model owners can embed an imperceptible signal into generated text, marking its origin. Most leading approaches seed an LLM's next-token sampling with a pseudo-random key that can later be recovered to identify the text as machine-generated, while only minimally altering the model's output distribution. However, these methods suffer from two related issues: (i) watermarks are brittle to simple surface-level edits such as paraphrasing or reordering; and (ii) adversaries can append unrelated, potentially harmful text that inherits the watermark, risking reputational damage to model owners. To address these issues, we introduce SimKey, a semantic key module that strengthens watermark robustness by tying key generation to the meaning of prior context. SimKey uses locality-sensitive hashing over semantic embeddings to ensure that paraphrased text yields the same watermark key, while unrelated or semantically shifted text produces a different one. Integrated with state-of-the-art watermarking schemes, SimKey improves watermark robustness to paraphrasing and translation while preventing harmful content from false attribution, establishing semantic-aware keying as a practical and extensible watermarking direction.

cs.CR↗

arXiv2025

We Are AI: Taking Control of Technology

Responsible AI (RAI) is the science and practice of ensuring the design, development, use, and oversight of AI are socially sustainable--benefiting diverse stakeholders while controlling the risks. Achieving this goal requires active engagement and participation from the broader public. This paper introduces "We are AI: Taking Control of Technology," a public education course that brings the topics of AI and RAI to the general audience in a peer-learning setting. We outline the goals behind the course's development, discuss the multi-year iterative process that shaped its creation, and summarize its content. We also discuss two offerings of We are AI to an active and engaged group of librarians and professional staff at New York University, highlighting successes and areas for improvement. The course materials, including a multilingual comic book series by the same name, are publicly available and can be used independently. By sharing our experience in creating and teaching We are AI, we aim to introduce these resources to the community of AI educators, researchers, and practitioners, supporting their public education efforts.

cs.CY↗

arXiv2025

Fragments to Facts: Partial-Information Fragment Inference from LLMs

Large language models (LLMs) can leak sensitive training data through memorization and membership inference attacks. Prior work has primarily focused on strong adversarial assumptions, including attacker access to entire samples or long, ordered prefixes, leaving open the question of how vulnerable LLMs are when adversaries have only partial, unordered sample information. For example, if an attacker knows a patient has "hypertension," under what conditions can they query a model fine-tuned on patient data to learn the patient also has "osteoarthritis?" In this paper, we introduce a more general threat model under this weaker assumption and show that fine-tuned LLMs are susceptible to these fragment-specific extraction attacks. To systematically investigate these attacks, we propose two data-blind methods: (1) a likelihood ratio attack inspired by methods from membership inference, and (2) a novel approach, PRISM, which regularizes the ratio by leveraging an external prior. Using examples from both medical and legal settings, we show that both methods are competitive with a data-aware baseline classifier that assumes access to labeled in-distribution data, underscoring their robustness.

cs.LG↗

arXiv2025

Do You Really Need Public Data? Surrogate Public Data for Differential Privacy on Tabular Data

Differentially private (DP) machine learning often relies on the availability of public data for tasks like privacy-utility trade-off estimation, hyperparameter tuning, and pretraining. While public data assumptions may be reasonable in text and image domains, they are less likely to hold for tabular data due to tabular data heterogeneity across domains. We propose leveraging powerful priors to address this limitation; specifically, we synthesize realistic tabular data directly from schema-level specifications - such as variable names, types, and permissible ranges - without ever accessing sensitive records. To that end, this work introduces the notion of "surrogate" public data - datasets generated independently of sensitive data, which consume no privacy loss budget and are constructed solely from publicly available schema or metadata. Surrogate public data are intended to encode plausible statistical assumptions (informed by publicly available information) into a dataset with many downstream uses in private mechanisms. We automate the process of generating surrogate public data with large language models (LLMs); in particular, we propose two methods: direct record generation as CSV files, and automated structural causal model (SCM) construction for sampling records. Through extensive experiments, we demonstrate that surrogate public tabular data can effectively replace traditional public data when pretraining differentially private tabular classifiers. To a lesser extent, surrogate public data are also useful for hyperparameter tuning of DP synthetic data generators, and for estimating the privacy-utility tradeoff.

cs.LG↗

arXiv2024

Are Data Experts Buying into Differentially Private Synthetic Data? Gathering Community Perspectives

Data privacy is a core tenet of responsible computing, and in the United States, differential privacy (DP) is the dominant technical operationalization of privacy-preserving data analysis. With this study, we qualitatively examine one class of DP mechanisms: private data synthesizers. To that end, we conducted semi-structured interviews with data experts: academics and practitioners who regularly work with data. Broadly, our findings suggest that quantitative DP benchmarks must be grounded in practitioner needs, while communication challenges persist. Participants expressed a need for context-aware DP solutions, focusing on parity between research outcomes on real and synthetic data. Our analysis led to three recommendations: (1) improve existing insufficient sanitized benchmarks; successful DP implementations require well-documented, partner-vetted use cases, (2) organizations using DP synthetic data should publish discipline-specific standards of evidence, and (3) tiered data access models could allow researchers to gradually access sensitive data based on demonstrated competence with high-privacy, low-fidelity synthetic data.

cs.HC↗

arXiv2024

Differential Privacy Under Class Imbalance: Methods and Empirical Insights

Imbalanced learning occurs in classification settings where the distribution of class-labels is highly skewed in the training data, such as when predicting rare diseases or in fraud detection. This class imbalance presents a significant algorithmic challenge, which can be further exacerbated when privacy-preserving techniques such as differential privacy are applied to protect sensitive training data. Our work formalizes these challenges and provides a number of algorithmic solutions. We consider DP variants of pre-processing methods that privately augment the original dataset to reduce the class imbalance; these include oversampling, SMOTE, and private synthetic data generation. We also consider DP variants of in-processing techniques, which adjust the learning algorithm to account for the imbalance; these include model bagging, class-weighted empirical risk minimization and class-weighted deep learning. For each method, we either adapt an existing imbalanced learning technique to the private setting or demonstrate its incompatibility with differential privacy. Finally, we empirically evaluate these privacy-preserving imbalanced learning methods under various data and distributional settings. We find that private synthetic data methods perform well as a data pre-processing step, while class-weighted ERMs are an alternative in higher-dimensional settings where private synthetic data suffers from the curse of dimensionality.

cs.LG↗

arXiv2024

FairlyUncertain: A Comprehensive Benchmark of Uncertainty in Algorithmic Fairness

Fair predictive algorithms hinge on both equality and trust, yet inherent uncertainty in real-world data challenges our ability to make consistent, fair, and calibrated decisions. While fairly managing predictive error has been extensively explored, some recent work has begun to address the challenge of fairly accounting for irreducible prediction uncertainty. However, a clear taxonomy and well-specified objectives for integrating uncertainty into fairness remains undefined. We address this gap by introducing FairlyUncertain, an axiomatic benchmark for evaluating uncertainty estimates in fairness. Our benchmark posits that fair predictive uncertainty estimates should be consistent across learning pipelines and calibrated to observed randomness. Through extensive experiments on ten popular fairness datasets, our evaluation reveals: (1) A theoretically justified and simple method for estimating uncertainty in binary settings is more consistent and calibrated than prior work; (2) Abstaining from binary predictions, even with improved uncertainty estimates, reduces error but does not alleviate outcome imbalances between demographic groups; (3) Incorporating consistent and calibrated uncertainty estimates in regression tasks improves fairness without any explicit fairness interventions. Additionally, our benchmark package is designed to be extensible and open-source, to grow with the field. By providing a standardized framework for assessing the interplay between uncertainty and fairness, FairlyUncertain paves the way for more equitable and trustworthy machine learning practices.

cs.LG↗

arXiv2024

Laboratory-Scale AI: Open-Weight Models are Competitive with ChatGPT Even in Low-Resource Settings

The rapid proliferation of generative AI has raised questions about the competitiveness of lower-parameter, locally tunable, open-weight models relative to high-parameter, API-guarded, closed-weight models in terms of performance, domain adaptation, cost, and generalization. Centering under-resourced yet risk-intolerant settings in government, research, and healthcare, we see for-profit closed-weight models as incompatible with requirements for transparency, privacy, adaptability, and standards of evidence. Yet the performance penalty in using open-weight models, especially in low-data and low-resource settings, is unclear. We assess the feasibility of using smaller, open-weight models to replace GPT-4-Turbo in zero-shot, few-shot, and fine-tuned regimes, assuming access to only a single, low-cost GPU. We assess value-sensitive issues around bias, privacy, and abstention on three additional tasks relevant to those topics. We find that with relatively low effort, very low absolute monetary cost, and relatively little data for fine-tuning, small open-weight models can achieve competitive performance in domain-adapted tasks without sacrificing generality. We then run experiments considering practical issues in bias, privacy, and hallucination risk, finding that open models offer several benefits over closed models. We intend this work as a case study in understanding the opportunity cost of reproducibility and transparency over for-profit state-of-the-art zero shot performance, finding this cost to be marginal under realistic settings.

cs.LG↗

arXiv2023

A Simple and Practical Method for Reducing the Disparate Impact of Differential Privacy

Differentially private (DP) mechanisms have been deployed in a variety of high-impact social settings (perhaps most notably by the U.S. Census). Since all DP mechanisms involve adding noise to results of statistical queries, they are expected to impact our ability to accurately analyze and learn from data, in effect trading off privacy with utility. Alarmingly, the impact of DP on utility can vary significantly among different sub-populations. A simple way to reduce this disparity is with stratification. First compute an independent private estimate for each group in the data set (which may be the intersection of several protected classes), then, to compute estimates of global statistics, appropriately recombine these group estimates. Our main observation is that naive stratification often yields high-accuracy estimates of population-level statistics, without the need for additional privacy budget. We support this observation theoretically and empirically. Our theoretical results center on the private mean estimation problem, while our empirical results center on extensive experiments on private data synthesis to demonstrate the effectiveness of stratification on a variety of private mechanisms. Overall, we argue that this straightforward approach provides a strong baseline against which future work on reducing utility disparities of DP mechanisms should be compared.

cs.CR↗

arXiv2023

I Open at the Close: A Deep Reinforcement Learning Evaluation of Open Streets Initiatives

The open streets initiative "opens" streets to pedestrians and bicyclists by closing them to cars and trucks. The initiative, adopted by many cities across North America, increases community space in urban environments. But could open streets also make cities safer and less congested? We study this question by framing the choice of which streets to open as a reinforcement learning problem. In order to simulate the impact of opening streets, we first compare models for predicting vehicle collisions given network and temporal data. We find that a recurrent graph neural network, leveraging the graph structure and the short-term temporal dependence of the data, gives the best predictive performance. Then, with the ability to simulate collisions and traffic, we frame a reinforcement learning problem to find which streets to open. We compare the streets in the NYC Open Streets program to those proposed by a Q-learning algorithm. We find that the streets proposed by the Q-learning algorithm have reliably better outcomes, while streets in the program have similar outcomes to randomly selected streets. We present our work as a step toward principally choosing which streets to open for safer and less congested cities. All our code and data are available on Github.

cs.LG↗

arXiv2023

Top-down Green-ups: Satellite Sensing and Deep Models to Predict Buffelgrass Phenology

An invasive species of grass known as "buffelgrass" contributes to severe wildfires and biodiversity loss in the Southwest United States. We tackle the problem of predicting buffelgrass "green-ups" (i.e. readiness for herbicidal treatment). To make our predictions, we explore temporal, visual and multi-modal models that combine satellite sensing and deep learning. We find that all of our neural-based approaches improve over conventional buffelgrass green-up models, and discuss how neural model deployment promises significant resource savings.

cs.CV↗