← Search

Tian Dong

2 accepted papers

2026

Authority Backdoor: A Certifiable Backdoor Mechanism for Authoring DNNs

AAAI 2026technical

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 proact

Cited by 0SourcePDFScholar