← Search

Zhuomeng Zhang

2 accepted papers

2025

Boosting the Uniqueness of Neural Networks Fingerprints with Informative Triggers

NeurIPS 2025poster

One prerequisite for secure and reliable artificial intelligence services is tracing the copyright of backend deep neural networks. In the black-box scenario, the copyright of deep neural networks can be traced by their fingerprints, i.e., their outputs on a series of fingerprinting triggers. The…

Cited by 0SourceScholar
2025

Evading Data Provenance in Deep Neural Networks

ICCV 2025poster

Modern over-parameterized deep models are highly data-dependent, with large scale general-purpose and domain-specific datasets serving as the bedrock for rapid advancements. However, many datasets are proprietary or contain sensitive information, making unrestricted model training problematic. In th…