You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content
Authors: Xinlei He, Savvas Zannettou, Yun Shen, Yang Zhang | Published: 2023-08-10
Prompt leaking
Effective Prompt Extraction from Language Models
Authors: Yiming Zhang, Nicholas Carlini, Daphne Ippolito | Published: 2023-07-13 | Updated: 2024-08-07
Undetectable Watermarks for Language Models
Authors: Miranda Christ, Sam Gunn, Or Zamir | Published: 2023-05-25
Killing four birds with one Gaussian process: the relation between different test-time attacks
Authors: Kathrin Grosse, Michael T. Smith, Michael Backes | Published: 2018-06-06 | Updated: 2020-11-29