# Authority Backdoor: A Certifiable Backdoor Mechanism for Authoring DNNs

Source: [Authority Backdoor: A Certifiable Backdoor Mechanism for Authoring DNNs](<https://www.sota2.com/research/paper/693ba1706cfd488761a550ea>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-13T05:01:26.895Z

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

Published: 2025-12-11T12:50:39.000Z

## 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's utility, such that it performs normally only in the presence of a specific trigger (e.g., a hardware fingerprint). But in its absence, the DNN's performance degrades to be useless. To further enhance the security of the proposed authority scheme, the certifiable robustness is integrated to prevent an adaptive attacker from removing the implanted backdoor. The resulting framework establishes a secure authority mechanism for DNNs, combining access control with certifiable robustness against adversarial attacks. Extensive experiments on diverse architectures and datasets validate the effectiveness and certifiable robustness of the proposed framework.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on CIFAR-10 (acc\_auth, acc\_clean)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-acc_auth-acc_clean.md>): Image Classification; CIFAR-10; Acc (Auth): 94.13.

- [Robust Image Classification on GTSRB](<https://www.sota2.com/research/sota/robust-image-classification-on-gtsrb.md>): Image Classification; GTSRB; Natural Accuracy: 9.4.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2512.10600>)

[PDF](<https://arxiv.org/pdf/2512.10600.pdf>)
