An Investigation of the Vulnerabilities and Effects of Prompt-Tuning to Pre-Trained Language Models

Fotini Deligiannaki1 & Arne Peter Raulf1
1 Institute for AI Safety and Security, German Aerospace Center, Germany

Abstract Submitted: 13.04.2023
Accepted: 21.04.2023
Presented at the DataNinja Spring School 2023 Poster Session: 09.05.2023
Published online: 20.06.2023

Licence: Copyright (c) 2023 The Authors

This work is licensed under a Creative Commons Attribution 4.0 International License.

Extended Abstract

FotiniDeligiannaki_2023_springschool_dataninja_abstractDownload Extended Abstract

Poster

FotiniDeligiannaki_2023_springschool_dataninja_posterDownload Poster File