@inproceedings{li-etal-2023-sentence,
    title = "Sentence Embedding Leaks More Information than You Expect: Generative Embedding Inversion Attack to Recover the Whole Sentence",
    author = "Li, Haoran  and
      Xu, Mingshi  and
      Song, Yangqiu",
    editor = "Rogers, Anna  and
      Boyd-Graber, Jordan  and
      Okazaki, Naoaki",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2023.findings-acl.881/",
    doi = "10.18653/v1/2023.findings-acl.881",
    pages = "14022--14040",
    abstract = "Sentence-level representations are beneficial for various natural language processing tasks. It is commonly believed that vector representations can capture rich linguistic properties. Currently, large language models (LMs) achieve state-of-the-art performance on sentence embedding. However, some recent works suggest that vector representations from LMs can cause information leakage. In this work, we further investigate the information leakage issue and propose a generative embedding inversion attack (GEIA) that aims to reconstruct input sequences based only on their sentence embeddings. Given the black-box access to a language model, we treat sentence embeddings as initial tokens' representations and train or fine-tune a powerful decoder model to decode the whole sequences directly. We conduct extensive experiments to demonstrate that our generative inversion attack outperforms previous embedding inversion attacks in classification metrics and generates coherent and contextually similar sentences as the original inputs."
}