Overview

Privacy-preserving data analysis has become essential in the age of Machine Learning (ML) where access to vast amounts of data can provide gains over tuned algorithms. A large proportion of user-contributed data comes from natural language e.g., text transcriptions from voice assistants.

It is therefore important to curate NLP datasets while preserving the privacy of the users whose data is collected, and train ML models that only retain non-identifying user data.

The workshop aims to bring together practitioners and researchers from academia and industry to discuss the challenges and approaches to designing, building, verifying, and testing privacy preserving systems in the context of Natural Language Processing. 

Information about the workshop's topics of interest can be found in the Call for Papers.

Agenda

Venue: Hybrid (Virtual and Seattle, WA)

Zoom link: here

Date:  July 15, 2022 

Timezone: PDT – Pacific Daylight Time

08:30 - 09:00 Invited Talk

• Franziska Boenisch

09:00 - 09:15 Break

• Morning break

09:15 - 09:45 Research paper

• Differential Privacy in Natural Language Processing: The Story So Far

• Oleksandra Klymenko, Stephen Joseph Meisenbacher and Florian Matthes

09:45 - 10:15 Research paper

• The Impact of Differential Privacy on Group Disparity Mitigation

• Victor Petrén Bach Hansen, Atula Tejaswi Neerkaje, Ramit Sawhney, Lucie Flek and Anders Søgaard

10:15 - 10:30 Break

• Coffee break

10:30 - 11:00 Invited Talk

• Esha Ghosh

11:00 - 12:00 Break

• Lunch break

12:00 - 12:30 Research paper

• Training Text-to-Text Transformers with Privacy Guarantees

• Natalia Ponomareva, Jasmijn Bastings and Sergei Vassilvitskii

12:30 - 13:00 Research paper

• Privacy Leakage in Text Classification: A Data Extraction Approach

• Adel Elmahdy, Huseyin A. Inan and Robert Sim

13:00 - 13:15 Break

• Coffee break

13:15 - 13:45 Keynote Talk

• Ilya Mironov

13:45 - 14:10 Discussion

• Panel discussion

14:10 - 14:15 Wrap up

Key Dates

• Submission Deadline: April 20, 2022 (11.59pm UTC-12)

• Acceptance Notification: May 6, 2022

• Camera-ready versions: May 20, 2022

• Workshop: July 15, 2022

Keynote Speaker

• Ilya Mironov (Meta)

Invited Speakers

• Franziska Boenisch (Fraunhofer AISEC)

• Esha Ghosh (Microsoft)