English

IrisFP: Adversarial-Example-based Model Fingerprinting with Enhanced Uniqueness and Robustness

Cryptography and Security 2026-03-31 v2

Abstract

We propose IrisFP, a novel adversarial-example-based model fingerprinting framework that enhances both uniqueness and robustness by leveraging multi-boundary characteristics, multi-sample behaviors, and fingerprint discriminative power assessment to generate composite-sample fingerprints. Three key innovations make IrisFP outstanding: 1) It positions fingerprints near the intersection of all decision boundaries - unlike prior methods that target a single boundary - thus increasing the prediction margin without placing fingerprints deep inside target class regions, enhancing both robustness and uniqueness; 2) It constructs composite-sample fingerprints, each comprising multiple samples close to the multi-boundary intersection, to exploit collective behavior patterns and further boost uniqueness; and 3) It assesses the discriminative power of generated fingerprints using statistical separability metrics developed based on two reference model sets, respectively, for pirated and independently-trained models, retains the fingerprints with high discriminative power, and assigns fingerprint-specific thresholds to such retained fingerprints. Extensive experiments show that IrisFP consistently outperforms state-of-the-art methods, achieving reliable ownership verification by enhancing both robustness and uniqueness.

Keywords

Cite

@article{arxiv.2603.24996,
  title  = {IrisFP: Adversarial-Example-based Model Fingerprinting with Enhanced Uniqueness and Robustness},
  author = {Ziye Geng and Guang Yang and Yihang Chen and Changqing Luo},
  journal= {arXiv preprint arXiv:2603.24996},
  year   = {2026}
}

Comments

To appear in CVPR 2026

R2 v1 2026-07-01T11:38:25.870Z