Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Back to Paper
cs.CR

Local ID: 2603.24996v2

AI Summary: gemma4:e4b

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

By Ziye Geng, Guang Yang, Yihang Chen, Changqing Luo

Revision History Timeline

v13/26/2026
3/26/2026

No submitter comment provided.

v23/30/2026
3/30/2026

“To appear in CVPR 2026”

★ Version indexed in Explorer

Comparing v1 vs v2

Green = Added • Red = Removed

Title Comparison

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

Authors Comparison

No author changes.

v1 Comment

No comment for this version.

v2 Comment

“To appear in CVPR 2026”

Abstract Word Diff

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.
View Full Version History on arXiv