Authority Backdoor: A Certifiable Backdoor Mechanism for Authoring DNNs

Han Yang; Shaofeng Li; Tian Dong; Xiangyu Xu; Guangchi Liu; Zhen Ling

AAAI 2026technical0 citations

Authority Backdoor: A Certifiable Backdoor Mechanism for Authoring DNNs

Han Yang, Shaofeng Li, Tian Dong, Xiangyu Xu, Guangchi Liu, Zhen Ling

Abstract

Deep Neural Networks (DNNs), as valuable intellectual property, face unauthorized use. Existing protections, such as digital watermarking, are largely passive; they provide only post-hoc ownership verification and cannot actively prevent the illicit use of a stolen model. This work proposes a proactive protection scheme, dubbed ``Authority Backdoor," which embeds access constraints directly into the model. In particular, the scheme utilizes a backdoor learning framework to intrinsically lock a model

BibTeX

@inproceedings{aaai2026_authoritybackdoo,
  title = {Authority Backdoor: A Certifiable Backdoor Mechanism for Authoring DNNs},
  author = {Han Yang and Shaofeng Li and Tian Dong and Xiangyu Xu and Guangchi Liu and Zhen Ling},
  booktitle = {AAAI 2026},
  year = {2026}
}