TIBW: Task-Independent Backdoor Watermarking with Fine-Tuning Resilience for Pre-Trained Language Models
Pre-trained language models such as BERT, GPT-3, and T5 have made significant advancements in natural language processing (NLP). However, their widespread adoption raises concerns about intellectual property (IP) protection, as unauthorized use can undermine innovation. Watermarking has emerged as a...
Сохранить в:
| Главные авторы: | , , |
|---|---|
| Формат: | Artigo |
| Язык: | Inglês |
| Опубликовано: |
MDPI AG
2025-01-01
|
| Серии: | Mathematics |
| Предметы: | |
| Online-ссылка: | https://www.mdpi.com/2227-7390/13/2/272 |
| Метки: |
Нет меток, Требуется 1-ая метка записи!
|