@inproceedings{panaitescu-liess-etal-2025-poisonedparrot,
    title = "{P}oisoned{P}arrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models",
    author = "Panaitescu-Liess, Michael-Andrei  and
      Pathmanathan, Pankayaraj  and
      Kaya, Yigitcan  and
      Che, Zora  and
      An, Bang  and
      Zhu, Sicheng  and
      Agrawal, Aakriti  and
      Huang, Furong",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.naacl-long.415/",
    pages = "8173--8190",
    ISBN = "979-8-89176-189-6",
    abstract = "As the capabilities of large language models (LLMs) continue to expand, their usage has become increasingly prevalent. However, as reflected in numerous ongoing lawsuits regarding LLM-generated content, addressing copyright infringement remains a significant challenge. In this paper, we introduce PoisonedParrot: the first \textit{stealthy} data poisoning attack that induces an LLM to generate copyrighted content even when the model has not been directly trained on the specific copyrighted material. PoisonedParrot integrates small fragments of copyrighted text into the poison samples using an off-the-shelf LLM. Despite its simplicity, evaluated in a wide range of experiments, PoisonedParrot is surprisingly effective at priming the model to generate copyrighted content with no discernible side effects. Moreover, we discover that existing defenses are largely ineffective against our attack. Finally, we make the first attempt at mitigating copyright-infringement poisoning attacks by proposing a defense: ParrotTrap. We encourage the community to explore this emerging threat model further."
}