IrisFP: Adversarial-Example-based Model Fingerprinting with Enhanced Uniqueness and Robustness
About
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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Model Fingerprinting | CIFAR-100 | AUC100 | 52 | |
| Model Fingerprinting | MNIST | AUC0.985 | 47 | |
| Model Fingerprinting | CIFAR-10 | AUC1 | 47 | |
| Model Fingerprinting | Tiny-ImageNet | AUC1 | 45 | |
| Model Fingerprinting | Fashion MNIST | AUC99.2 | 40 | |
| Fingerprint Generation | Fashion MNIST | Time Overhead1 | 15 | |
| Model Ownership Verification | Tiny-ImageNet | Fidelity Score (FT)97.9 | 10 | |
| Model Ownership Verification | Fashion MNIST | Fidelity Transfer (FT)97.5 | 5 | |
| Model Ownership Verification | MNIST | Fidelity (FT)98.3 | 5 | |
| Model Ownership Verification | CIFAR-10 | FT98.1 | 5 |