Search Results for author:
Found 4 papers, 0 papers with code
Disentangling the Linguistic Competence of Privacy-Preserving BERT
Differential Privacy (DP) has been tailored to address the unique challenges of text-to-text privatization.
Guiding Text-to-Text Privatization by Syntax
Lacking the capability to produce surrogate texts that correlate with the structure of the sensitive texts, we encompass our analysis by transforming the privatization step into a candidate selection problem in which substitutions are directed to words with matching grammatical properties.
Driving Context into Text-to-Text Privatization
\textit{Metric Differential Privacy} enables text-to-text privatization by adding calibrated noise to the vector of a word derived from an embedding space and projecting this noisy vector back to a discrete vocabulary using a nearest neighbor search.
Demystifying the Effects of Non-Independence in Federated Learning
Specifically, we measure the alterations induced by block-cyclic sampling from the perspective of accuracy, fairness, and convergence rate.
