AdaLoc: Re-Key-Free, Risky-Free Adaptable Model Usage Control
Zihan Wang, Zhongkui Ma, Xinguo Feng, Chuan Yan, Dongge Liu, Ruoxi Sun, Derui Wang, Minhui Xue, Guangdong Bai
Key-based model usage control with adaptation restricted to an intrinsic subset of parameters, avoiding full re-keying within that update procedure.
The problem
Model updates can invalidate usage-control mechanisms designed for a fixed deployment. AdaLoc studies how authorised adaptation and lock preservation can be maintained together.
The method
A selected subset of parameters serves as an intrinsic access key and as the location of subsequent updates. Within this procedure, updating the key can restore the latest authorised model state without redistributing the entire network or performing full re-keying.
Evidence and scope
The analysis includes error bounds for key-restricted updates, supported by experiments on vision and language tasks. The update restriction is part of the mechanism: the result concerns adaptation through the selected key, rather than arbitrary modifications to every parameter.
The Paper and GitHub links above give the assumptions and implementation. CoreLocker provides the related usage-control context.
Citation
@inproceedings{wang2026rekeyfree,
author = {Wang, Zihan and Ma, Zhongkui and Feng, Xinguo and Yan, Chuan and Liu, Dongge and Sun, Ruoxi and Wang, Derui and Xue, Minhui and Bai, Guangdong},
title = {Re-Key-Free, Risky-Free: Adaptable Model Usage Control},
booktitle = {2026 IEEE 11th European Symposium on Security and Privacy (EuroS\&P)},
pages = {696--711},
year = {2026},
publisher = {IEEE},
doi = {10.1109/EuroSP68448.2026.00051}
}