Seeing Is Not Always Believing: Invisible Collision Attack and Defence on Pre-Trained Models

1 code implementation • 24 Sep 2023 • Minghang Deng, Zhong Zhang, Junming Shao

The typical paradigm is to pre-train a big deep learning model on large-scale data sets, and then fine-tune the model on small task-specific data sets for downstream tasks.

Data Poisoning