Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model Merging

arXiv:2404.05188v1 Announce Type: cross
Abstract: 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. Instead, it involves editing different upstream model parameters to absorb their downstream task capabilities. 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 in model …

abstract arxiv collection computing cs.ai cs.cl cs.cr data devices editing empowerment gpus language language model large language large language model merging parameters protection robustness training training data type