Search Results for author:
Found 7 papers, 4 papers with code
Differentially Private Learning Needs Better Model Initialization and Self-Distillation
Differentially private SGD (DPSGD) enables privacy-preserving training of language models, but often reduces utility, diversity, and linguistic quality.
Backpropagation Clipping for Deep Learning with Differential Privacy
We present backpropagation clipping, a novel variant of differentially private stochastic gradient descent (DP-SGD) for privacy-preserving deep learning.
Prediction Sensitivity: Continual Audit of Counterfactual Fairness in Deployed Classifiers
As AI-based systems increasingly impact many areas of our lives, auditing these systems for fairness is an increasingly high-stakes problem.
Towards Auditability for Fairness in Deep Learning
Group fairness metrics can detect when a deep learning model behaves differently for advantaged and disadvantaged groups, but even models that score well on these metrics can make blatantly unfair predictions.
Towards a Measure of Individual Fairness for Deep Learning
Deep learning has produced big advances in artificial intelligence, but trained neural networks often reflect and amplify bias in their training data, and thus produce unfair predictions.
Chorus: a Programming Framework for Building Scalable Differential Privacy Mechanisms
Differential privacy is fast becoming the gold standard in enabling statistical analysis of data while protecting the privacy of individuals.
Cryptography and Security
Towards Practical Differential Privacy for SQL Queries
To meet these requirements we propose elastic sensitivity, a novel method for approximating the local sensitivity of queries with general equijoins.
Cryptography and Security Databases
