What is it about?

Model merging is a promising lightweight model empowerment technique that does not rely on expensive computing devices (e.g., GPUs) or require the collection of specific training data. However, uncertified model merging can infringe upon the Intellectual Property (IP) rights of the original upstream models. In this paper, we conduct the first study on the robustness of IP protection methods under model merging scenarios.

Featured Image

Read the Original

This page is a summary of: Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model Merging, November 2023, ACM (Association for Computing Machinery),
DOI: 10.1145/3689217.3690614.
You can read the full text:

Read

Contributors

The following have contributed to this page