Single-Model Attribution of Generative Models Through Final-Layer Inversion

arXiv:2306.06210v4 Announce Type: replace-cross
Abstract: Recent breakthroughs in generative modeling have sparked interest in practical single-model attribution. Such methods predict whether a sample was generated by a specific generator or not, for instance, to prove intellectual property theft. However, previous works are either limited to the closed-world setting or require undesirable changes to the generative model. We address these shortcomings by, first, viewing single-model attribution through the lens of anomaly detection. Arising from this change of perspective, we propose FLIPAD, …

abstract arxiv attribution cs.cv cs.lg generated generative generative modeling generative models generator instance intellectual property layer modeling practical property prove sample theft through type world