no code implementations • 17 Oct 2023 • Stefan Arnold, Nils Kemmerzell, Annika Schreiner
Differential Privacy (DP) has been tailored to address the unique challenges of text-to-text privatization.
no code implementations • 2 Jun 2023 • Stefan Arnold, Dilara Yesilbas, Sven Weinzierl
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.
no code implementations • 2 Jun 2023 • Stefan Arnold, Dilara Yesilbas, Sven Weinzierl
\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.
no code implementations • 20 Mar 2021 • Stefan Arnold, Dilara Yesilbas
Specifically, we measure the alterations induced by block-cyclic sampling from the perspective of accuracy, fairness, and convergence rate.