research
∙
07/16/2021
TEM: High Utility Metric Differential Privacy on Text
Ensuring the privacy of users whose data are used to train Natural Langu...
share
research
∙
07/16/2021
BRR: Preserving Privacy of Text Data Efficiently on Device
With the use of personal devices connected to the Internet for tasks suc...
research
∙
07/07/2021
On Codomain Separability and Label Inference from (Noisy) Loss Functions
Machine learning classifiers rely on loss functions for performance eval...
research
∙
05/18/2021
Label Inference Attacks from Log-loss Scores
Log-loss (also known as cross-entropy loss) metric is ubiquitously used ...
research
∙
04/23/2021
On a Utilitarian Approach to Privacy Preserving Text Generation
Differentially-private mechanisms for text generation typically add care...
research
∙
12/10/2020
Research Challenges in Designing Differentially Private Text Generation Mechanisms
Accurately learning from user data while ensuring quantifiable privacy g...
research
∙
10/22/2020
A Differentially Private Text Perturbation Method Using a Regularized Mahalanobis Metric
Balancing the privacy-utility tradeoff is a crucial requirement of many ...
research
∙
09/27/2020
Differentially Private Adversarial Robustness Through Randomized Perturbations
Deep Neural Networks, despite their great success in diverse domains, ar...
research
∙
09/17/2020
On Primes, Log-Loss Scores and (No) Privacy
Membership Inference Attacks exploit the vulnerabilities of exposing mod...
research
∙
10/20/2019
Leveraging Hierarchical Representations for Preserving Privacy and Utility in Text
Guaranteeing a certain level of user privacy in an arbitrary piece of te...
research
∙
10/20/2019
Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbations
Accurately learning from user data while providing quantifiable privacy ...
research
∙
03/26/2019
Privacy-preserving Active Learning on Sensitive Data for User Intent Classification
Active learning holds promise of significantly reducing data annotation ...
research
∙
01/17/2019
