Revisiting Black-Box Model Ownership Verification through Information Theory 文章

arXiv:2409.06130v2 Announce Type: replace-cross Abstract: Modern machine learning models require substantial computational resources and data to train, making them valuable intellectual property. Model watermarking has emerged as a practical solution for black-box ownership verification, but existing methods suffer from a persistent trade-off between robustness and predictive utility. In this work, we analyze this limitation from an information-theoretic perspective and identify a fundamental capacity crisis: relying solely on predicted labels provides insufficient capacity to embed robust ownership signals without degrading accuracy. To deal with it, we propose a new black-box ownership verification framework that leverages the top-k output. By exploiting this richer output space, our approach increases the effective capacity available for watermarking while preserving predictive performance.