Saved in:
Bibliographic Details
Main Authors: Zheng, Amber Yijia, Yeh, Raymond A.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.15320
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912162680668160
author Zheng, Amber Yijia
Yeh, Raymond A.
author_facet Zheng, Amber Yijia
Yeh, Raymond A.
contents Model immunization is an emerging direction that aims to mitigate the potential risk of misuse associated with open-sourced models and advancing adaptation methods. The idea is to make the released models' weights difficult to fine-tune on certain harmful applications, hence the name ``immunized''. Recent work on model immunization focuses on the single-concept setting. However, models need to be immunized against multiple concepts in real-world situations. To address this gap, we propose an immunization algorithm that, simultaneously, learns a single ``difficult initialization'' for adaptation methods over a set of concepts. We achieve this by incorporating a differentiable merging layer that combines a set of model weights adapted over multiple concepts. In our experiments, we demonstrate the effectiveness of multi-concept immunization by generalizing prior work's experiment setup of re-learning and personalization adaptation to multiple concepts.
format Preprint
id arxiv_https___arxiv_org_abs_2412_15320
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-concept Model Immunization through Differentiable Model Merging
Zheng, Amber Yijia
Yeh, Raymond A.
Computer Vision and Pattern Recognition
Model immunization is an emerging direction that aims to mitigate the potential risk of misuse associated with open-sourced models and advancing adaptation methods. The idea is to make the released models' weights difficult to fine-tune on certain harmful applications, hence the name ``immunized''. Recent work on model immunization focuses on the single-concept setting. However, models need to be immunized against multiple concepts in real-world situations. To address this gap, we propose an immunization algorithm that, simultaneously, learns a single ``difficult initialization'' for adaptation methods over a set of concepts. We achieve this by incorporating a differentiable merging layer that combines a set of model weights adapted over multiple concepts. In our experiments, we demonstrate the effectiveness of multi-concept immunization by generalizing prior work's experiment setup of re-learning and personalization adaptation to multiple concepts.
title Multi-concept Model Immunization through Differentiable Model Merging
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.15320