Attesting Distributional Properties of Training Data for Machine Learning
The success of machine learning (ML) has been accompanied by increased concerns about its trustworthiness. Several jurisdictions are preparing ML regulatory frameworks. One such concern is ensuring that model training data has desirable distributional properties for certain sensitive attributes. For example, draft regulations indicate that model trainers are required to show that training datasets have specific distributional properties, such as reflecting diversity of the population. We propose the notion of property attestation allowing a prover (e.g., model trainer) to demonstrate relevant distributional properties of training data to a verifier (e.g., a customer) without revealing the data. We present an effective hybrid property attestation combining property inference with cryptographic mechanisms.
Code (1)
Tasks
DiversitySimilar Papers 제목 키워드 기반
Distributionally Robust Bayesian Optimization with $\varphi$-divergences
The study of robustness has received much attention due to its inevitability in data-driven settings where many systems face uncertainty. One such example of concern is Bayesian Optimization (BO), where uncertainty is mu…
Bayesian OptimizationA Distributional Framework for Data Valuation
Shapley value is a classic notion from game theory, historically used to quantify the contributions of individuals within groups, and more recently applied to assign values to data points when training machine learning m…
Data ValuationLearning Against Distributional Uncertainty: On the Trade-off Between Robustness and Specificity
Trustworthy machine learning aims at combating distributional uncertainties in training data distributions compared to population distributions. Typical treatment frameworks include the Bayesian approach, (min-max) distr…
Generalization BoundsSpecificityEstimating Distributional Treatment Effects in Randomized Experiments: Machine Learning for Variance Reduction
We propose a novel regression adjustment method designed for estimating distributional treatment effect parameters in randomized experiments. Randomized experiments have been extensively used to estimate treatment effect…
regressionvalidConfidence Regions in Wasserstein Distributionally Robust Estimation
Wasserstein distributionally robust optimization estimators are obtained as solutions of min-max problems in which the statistician selects a parameter minimizing the worst-case loss among all probability models within a…