2023

Protecting Language Generation Models via Invisible Watermarking

Zhao, Xuandong, Wang, Yu-Xiang, Li, Lei

Understand

Language generation models have been an increasingly powerful enabler for many applications.

  • Many such models offer free or affordable API access, which makes them potentially vulnerable to model extraction attacks through distillation.
  • To protect intellectual property (IP) and ensure fair use of these models, various techniques such as lexical watermarking and synonym replacement have been proposed.
  • However, these methods can be nullified by obvious countermeasures such as "synonym randomization".

Reading the bibliography…