A Collocation-based Method for Addressing Challenges in Word-level Metric Differential Privacy
Meisenbacher, Stephen, Chevli, Maulik, Matthes, Florian
–arXiv.org Artificial Intelligence
Applications of Differential Privacy (DP) in NLP must distinguish between the syntactic level on which a proposed mechanism operates, often taking the form of $\textit{word-level}$ or $\textit{document-level}$ privatization. Recently, several word-level $\textit{Metric}$ Differential Privacy approaches have been proposed, which rely on this generalized DP notion for operating in word embedding spaces. These approaches, however, often fail to produce semantically coherent textual outputs, and their application at the sentence- or document-level is only possible by a basic composition of word perturbations. In this work, we strive to address these challenges by operating $\textit{between}$ the word and sentence levels, namely with $\textit{collocations}$. By perturbing n-grams rather than single words, we devise a method where composed privatized outputs have higher semantic coherence and variable length. This is accomplished by constructing an embedding model based on frequently occurring word groups, in which unigram words co-exist with bi- and trigram collocations. We evaluate our method in utility and privacy tests, which make a clear case for tokenization strategies beyond the word level.
arXiv.org Artificial Intelligence
Jun-30-2024
- Country:
- Oceania > Australia
- New South Wales > Sydney (0.04)
- North America
- United States
- Maryland > Baltimore (0.04)
- California (0.04)
- Washington > King County
- Seattle (0.04)
- New York > New York County
- New York City (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- Michigan > Washtenaw County
- Ann Arbor (0.04)
- Colorado > Denver County
- Denver (0.04)
- Canada > Ontario
- Toronto (0.04)
- United States
- Europe
- Italy (0.04)
- Sweden > Uppsala County
- Uppsala (0.04)
- Spain > Valencian Community
- Valencia Province > Valencia (0.04)
- Middle East > Malta
- Germany > Bavaria
- Upper Bavaria > Munich (0.04)
- Denmark > Capital Region
- Copenhagen (0.04)
- Belgium > Brussels-Capital Region
- Brussels (0.04)
- Asia
- Singapore (0.04)
- Middle East > Jordan (0.04)
- Oceania > Australia
- Genre:
- Research Report > New Finding (0.46)
- Industry:
- Information Technology > Security & Privacy (0.93)
- Technology: