Single-Model Attribution of Generative Models Through Final-Layer Inversion
This addresses the need for proving intellectual property theft without requiring changes to generative models, though it is incremental as it builds on existing attribution methods.
The paper tackles the problem of single-model attribution for generative models in the open-world setting, proposing FLIPAD based on final-layer inversion and anomaly detection, and demonstrates its effectiveness with theoretical and experimental results.
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, a new approach for single-model attribution in the open-world setting based on final-layer inversion and anomaly detection. We show that the utilized final-layer inversion can be reduced to a convex lasso optimization problem, making our approach theoretically sound and computationally efficient. The theoretical findings are accompanied by an experimental study demonstrating the effectiveness of our approach and its flexibility to various domains.