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

Mike Laszkiewicz, Jonas Ricker, Johannes Lederer, Asja Fischer
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26007-26042, 2024.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-laszkiewicz24a, title = {Single-Model Attribution of Generative Models Through Final-Layer Inversion}, author = {Laszkiewicz, Mike and Ricker, Jonas and Lederer, Johannes and Fischer, Asja}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {26007--26042}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/laszkiewicz24a/laszkiewicz24a.pdf}, url = {https://proceedings.mlr.press/v235/laszkiewicz24a.html}, 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.} }
Endnote
%0 Conference Paper %T Single-Model Attribution of Generative Models Through Final-Layer Inversion %A Mike Laszkiewicz %A Jonas Ricker %A Johannes Lederer %A Asja Fischer %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-laszkiewicz24a %I PMLR %P 26007--26042 %U https://proceedings.mlr.press/v235/laszkiewicz24a.html %V 235 %X 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.
APA
Laszkiewicz, M., Ricker, J., Lederer, J. & Fischer, A.. (2024). Single-Model Attribution of Generative Models Through Final-Layer Inversion. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:26007-26042 Available from https://proceedings.mlr.press/v235/laszkiewicz24a.html.

Related Material