Catch-Only-One: Non-Transferable Examples for Model-Specific Authorization

ICLR 2026 Conference Submission10781 Authors

Keywords: Neural Networks, Model Specificity, Non-generalizable Examples

Abstract:

Recent AI regulations call for data that remain useful for innovation while resistant to misuse, balancing utility with protection at the model level. Existing approaches either perturb data to make it unlearnable or retrain models to suppress transfer, but neither governs inference by unknown models, and both typically require control over training.
We propose non-transferable examples (NEs), a training-free and data-agnostic input-side usage-control mechanism. We recode inputs within a model-specific low-sensitivity subspace, preserving outputs for the authorized model while reducing performance on unauthorized models through subspace misalignment. We establish formal bounds that guarantee utility for the authorized model and quantify deviation for unauthorized ones, with the Hoffman-Wielandt inequality linking degradation to spectral differences. Empirically, NEs retain performance on diverse vision backbones and state-of-the-art vision-language models under common preprocessing, while non-targets collapse even under severe distortions. These results establish NEs as a practical means to preserve intended data utility while preventing unauthorized exploitation.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Submission Number: 10781