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

TL;DR

This paper introduces FLIPAD, a novel method for single-model attribution of generative models in open-world scenarios, utilizing final-layer inversion and anomaly detection for accurate and efficient identification.

Contribution

The paper proposes FLIPAD, a new approach that leverages final-layer inversion and anomaly detection for open-world single-model attribution, with a convex optimization formulation.

Findings

Effective in open-world attribution scenarios

Theoretically grounded via convex optimization

Demonstrates flexibility across domains

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, 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.