research
∙
05/23/2023
Selective Pre-training for Private Fine-tuning
Suppose we want to train text prediction models in email clients or word...
share
research
∙
06/09/2022
Adversarial Noises Are Linearly Separable for (Nearly) Random Neural Networks
Adversarial examples, which are usually generated for specific inputs wi...
research
∙
06/06/2022
Per-Instance Privacy Accounting for Differentially Private Stochastic Gradient Descent
Differentially private stochastic gradient descent (DP-SGD) is the workh...
research
∙
11/01/2021
Indiscriminate Poisoning Attacks Are Shortcuts
Indiscriminate data poisoning attacks, which add imperceptible perturbat...
research
∙
10/13/2021
Differentially Private Fine-tuning of Language Models
We give simpler, sparser, and faster algorithms for differentially priva...
research
∙
06/17/2021
Large Scale Private Learning via Low-rank Reparametrization
We propose a reparametrization scheme to address the challenges of apply...
research
∙
02/25/2021
Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning
The privacy leakage of the model about the training data can be bounded ...
research
∙
07/21/2020
Membership Inference with Privately Augmented Data Endorses the Benign while Suppresses the Adversary
Membership inference (MI) in machine learning decides whether a given ex...
research
∙
11/26/2019
Gradient Perturbation is Underrated for Differentially Private Convex Optimization
Gradient perturbation, widely used for differentially private optimizati...
research
∙
03/17/2019