Search Results for author:
Found 13 papers, 1 papers with code
Private Release of Text Embedding Vectors
Ensuring strong theoretical privacy guarantees on text data is a challenging problem which is usually attained at the expense of utility.
On Log-Loss Scores and (No) Privacy
In this paper, we show that a malicious modeler, upon obtaining access to the Log-Loss scores on its predictions, can exploit this information to infer all the ground truth labels of arbitrary test datasets with full accuracy.
A Differentially Private Text Perturbation Method Using Regularized Mahalanobis Metric
In this paper, we propose a text perturbation mechanism based on a carefully designed regularized variant of the Mahalanobis metric to overcome this problem.
Reconstructing Test Labels from Noisy Loss Functions
Machine learning classifiers rely on loss functions for performance evaluation, often on a private (hidden) dataset.
Label Inference Attacks from Log-loss Scores
Log-loss (also known as cross-entropy loss) metric is ubiquitously used across machine learning applications to assess the performance of classification algorithms.
On a Utilitarian Approach to Privacy Preserving Text Generation
This is because the nearest neighbor to the noised input is likely to be the original input.
Research Challenges in Designing Differentially Private Text Generation Mechanisms
Such mechanisms add privacy preserving noise to vectorial representations of text in high dimension and return a text based projection of the noisy vectors.
A Differentially Private Text Perturbation Method Using a Regularized Mahalanobis Metric
Balancing the privacy-utility tradeoff is a crucial requirement of many practical machine learning systems that deal with sensitive customer data.
Differentially Private Adversarial Robustness Through Randomized Perturbations
Deep Neural Networks, despite their great success in diverse domains, are provably sensitive to small perturbations on correctly classified examples and lead to erroneous predictions.
On Primes, Log-Loss Scores and (No) Privacy
Membership Inference Attacks exploit the vulnerabilities of exposing models trained on customer data to queries by an adversary.
Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbations
We conduct privacy audit experiments against 2 baseline models and utility experiments on 3 datasets to demonstrate the tradeoff between privacy and utility for varying values of epsilon on different task types.
Leveraging Hierarchical Representations for Preserving Privacy and Utility in Text
In this work, we explore word representations in Hyperbolic space as a means of preserving privacy in text.
Privacy-preserving Active Learning on Sensitive Data for User Intent Classification
Active learning holds promise of significantly reducing data annotation costs while maintaining reasonable model performance.
