How reparametrization trick broke differentially-private text
representation learning

v1v2 (latest)

How reparametrization trick broke differentially-private text representation learning

24 February 2022

ArXiv (abs)PDF HTML

Papers citing "How reparametrization trick broke differentially-private text representation learning"

9 / 9 papers shown

Title
Private Language Models via Truncated Laplacian Mechanism Tianhao Huang Tao Yang Ivan Habernal Lijie Hu Di Wang 64 1 0 10 Oct 2024
DP-NMT: Scalable Differentially-Private Machine Translation Timour Igamberdiev Doan Nam Long Vu Felix Künnecke Zhuo Yu Jannik Holmer Ivan Habernal 91 7 0 24 Nov 2023
A Neighbourhood-Aware Differential Privacy Mechanism for Static Word Embeddings Danushka Bollegala Shuichi Otake T. Machide Ken-ichi Kawarabayashi 136 4 0 19 Sep 2023
Trade-Offs Between Fairness and Privacy in Language Modeling Cleo Matzken Steffen Eger Ivan Habernal SILM 112 6 0 24 May 2023
DP-BART for Privatized Text Rewriting under Local Differential Privacy Timour Igamberdiev Ivan Habernal 91 18 0 15 Feb 2023
Privacy-Preserving Models for Legal Natural Language Processing Ying Yin Ivan Habernal PILM AILaw 69 8 0 05 Nov 2022
Differentially Private Language Models for Secure Data Sharing Justus Mattern Zhijing Jin Benjamin Weggenmann Bernhard Schoelkopf Mrinmaya Sachan SyDa 104 52 0 25 Oct 2022
DP-Rewrite: Towards Reproducibility and Transparency in Differentially Private Text Rewriting Timour Igamberdiev Thomas Arnold Ivan Habernal 90 20 0 22 Aug 2022
Differential Privacy in Natural Language Processing: The Story So Far Oleksandra Klymenko Stephen Meisenbacher Florian Matthes 62 16 0 17 Aug 2022