Search Results for author:
Found 14 papers, 6 papers with code
Fragments to Facts: Partial-Information Fragment Inference from LLMs
Large language models (LLMs) can leak sensitive training data through memorization and membership inference attacks.
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.
Differential Privacy Under Class Imbalance: Methods and Empirical Insights
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.
FairlyUncertain: A Comprehensive Benchmark of Uncertainty in Algorithmic Fairness
Our benchmark posits that fair predictive uncertainty estimates should be consistent across learning pipelines and calibrated to observed randomness.
Sharper Bounds for Chebyshev Moment Matching with Applications to Differential Privacy and Beyond
We illustrate a second application of our new moment-based recovery bound in numerical linear algebra: by improving an approach of Braverman, Krishnan, and Musco [STOC 2022], our result yields a faster algorithm for estimating the spectral density of a symmetric matrix up to small error in the Wasserstein distance.
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.
A Simple and Practical Method for Reducing the Disparate Impact of Differential Privacy
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.
I Open at the Close: A Deep Reinforcement Learning Evaluation of Open Streets Initiatives
In order to simulate the impact of opening streets, we first compare models for predicting vehicle collisions given network and temporal data.
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.
The Possibility of Fairness: Revisiting the Impossibility Theorem in Practice
The ``impossibility theorem'' -- which is considered foundational in algorithmic fairness literature -- asserts that there must be trade-offs between common notions of fairness and performance when fitting statistical models, except in two special cases: when the prevalence of the outcome being predicted is equal across groups, or when a perfectly accurate predictor is used.
Critical Perspectives: A Benchmark Revealing Pitfalls in PerspectiveAPI
Detecting "toxic" language in internet content is a pressing social and technical challenge.
Counterfactual Fairness Is Basically Demographic Parity
Making fair decisions is crucial to ethically implementing machine learning algorithms in social settings.
Spending Privacy Budget Fairly and Wisely
Our methods are based on the insights that feature importance can inform how privacy budget is allocated, and, further, that per-group feature importance and fairness-related performance objectives can be incorporated in the allocation.
Differentially Private Synthetic Data: Applied Evaluations and Enhancements
Differentially private data synthesis protects personal details from exposure, and allows for the training of differentially private machine learning models on privately generated datasets.
