Revisiting Black-Box Model Ownership Verification through Information Theory
Quick summary
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 own
Key takeaways
- 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 own
Why it matters
“Revisiting Black-Box Model Ownership Verification through Information Theory” should be evaluated beyond branding and benchmark scores. Its practical importance will emerge in task accuracy, latency, unit cost, safety and integration with real workflows.
Member comments