Search Results for author:
Found 13 papers, 4 papers with code
Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment Settings
Deploying machine learning models in safety-critical domains poses a key challenge: ensuring reliable model performance on downstream user data without access to ground truth labels for direct validation.
Private Rate-Constrained Optimization with Applications to Fair Learning
To address this, we develop RaCO-DP, a DP variant of the Stochastic Gradient Descent-Ascent (SGDA) algorithm which solves the Lagrangian formulation of rate constraint problems.
On the Privacy Risk of In-context Learning
We show that deploying prompted models presents a significant privacy risk for the data used within the prompt by instantiating a highly effective membership inference attack.
Regulation Games for Trustworthy Machine Learning
Existing work on trustworthy machine learning (ML) often concentrates on individual aspects of trust, such as fairness or privacy.
Learning with Impartiality to Walk on the Pareto Frontier of Fairness, Privacy, and Utility
Deploying machine learning (ML) models often requires both fairness and privacy guarantees.
Proof-of-Learning is Currently More Broken Than You Think
They empirically argued the benefit of this approach by showing how spoofing--computing a proof for a stolen model--is as expensive as obtaining the proof honestly by training the model.
$p$-DkNN: Out-of-Distribution Detection Through Statistical Testing of Deep Representations
We introduce $p$-DkNN, a novel inference procedure that takes a trained deep neural network and analyzes the similarity structures of its intermediate hidden representations to compute $p$-values associated with the end-to-end model prediction.
Tubes Among Us: Analog Attack on Automatic Speaker Identification
Recent years have seen a surge in the popularity of acoustics-enabled personal devices powered by machine learning.
SoK: Machine Learning Governance
The application of machine learning (ML) in computer systems introduces not only many benefits but also risks to society.
Dataset Inference: Ownership Resolution in Machine Learning
We thus introduce $dataset$ $inference$, the process of identifying whether a suspected model copy has private knowledge from the original model's dataset, as a defense against model stealing.
Proof-of-Learning: Definitions and Practice
In particular, our analyses and experiments show that an adversary seeking to illegitimately manufacture a proof-of-learning needs to perform *at least* as much work than is needed for gradient descent itself.
A Human-in-the-loop Framework to Construct Context-aware Mathematical Notions of Outcome Fairness
Our family of fairness notions corresponds to a new interpretation of economic models of Equality of Opportunity (EOP), and it includes most existing notions of fairness as special cases.
Disparate Vulnerability to Membership Inference Attacks
Differential privacy bounds disparate vulnerability but can significantly reduce the accuracy of the model.
