Strong Copyright Protection for Language Models via Adaptive Model Fusion

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Abad, Javier, Donhauser, Konstantin, Pinto, Francesco, Yang, Fanny
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917736338161664
author Abad, Javier
Donhauser, Konstantin
Pinto, Francesco
Yang, Fanny
author_facet Abad, Javier
Donhauser, Konstantin
Pinto, Francesco
Yang, Fanny
contents The risk of language models unintentionally reproducing copyrighted material from their training data has led to the development of various protective measures. In this paper, we propose model fusion as an effective solution to safeguard against copyright infringement. In particular, we introduce Copyright-Protecting Fusion (CP-Fuse), an algorithm that adaptively combines language models to minimize the reproduction of protected materials. CP-Fuse is inspired by the recently proposed Near-Access Free (NAF) framework and additionally incorporates a desirable balancing property that we demonstrate prevents the reproduction of memorized training data. Our results show that CP-Fuse significantly reduces the memorization of copyrighted content while maintaining high-quality text and code generation. Furthermore, we demonstrate how CP-Fuse can be integrated with other techniques for enhanced protection.
format Preprint
id arxiv_https___arxiv_org_abs_2407_20105
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Strong Copyright Protection for Language Models via Adaptive Model Fusion
Abad, Javier
Donhauser, Konstantin
Pinto, Francesco
Yang, Fanny
Machine Learning
Cryptography and Security
The risk of language models unintentionally reproducing copyrighted material from their training data has led to the development of various protective measures. In this paper, we propose model fusion as an effective solution to safeguard against copyright infringement. In particular, we introduce Copyright-Protecting Fusion (CP-Fuse), an algorithm that adaptively combines language models to minimize the reproduction of protected materials. CP-Fuse is inspired by the recently proposed Near-Access Free (NAF) framework and additionally incorporates a desirable balancing property that we demonstrate prevents the reproduction of memorized training data. Our results show that CP-Fuse significantly reduces the memorization of copyrighted content while maintaining high-quality text and code generation. Furthermore, we demonstrate how CP-Fuse can be integrated with other techniques for enhanced protection.
title Strong Copyright Protection for Language Models via Adaptive Model Fusion
topic Machine Learning
Cryptography and Security
url https://arxiv.org/abs/2407.20105