Papers by Benjamin Weggenmann
The Limits of Word Level Differential Privacy (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods to anonymize textual data have several shortcomings . authors show that they can overcome these weaknesses and offer a formal privacy guarantee . |
| Approach: | They propose a method that circumvents most of the identified weaknesses and offers a formal privacy guarantee. |
| Outcome: | The proposed method outperforms the proposed methods in thourough experimentation and shows superior performance. |
Differentially Private Language Models for Secure Data Sharing (2022.emnlp-main)
Copied to clipboard
| Challenge: | a variety of deanonymization attacks allow the re-identification of individuals from tabular data. |
| Approach: | They propose to train a language model in a differentially private manner and sample data from it . they find that the model generates fluent textual datasets with privacy guarantees . |
| Outcome: | The proposed methods outperform direct classifiers with DP-SGD in the real-world. |