Text Embeddings Reveal (Almost) As Much As Text
John Morris, Volodymyr Kuleshov, Vitaly Shmatikov, Alexander Rush
Abstract
How much private information do text embeddings reveal about the original text? We investigate the problem of embedding inversion, reconstructing the full text represented in dense text embeddings. We frame the problem as controlled generation: generating text that, when reembedded, is close to a fixed point in latent space. We find that although a naive model conditioned on the embedding performs poorly, a multi-step method that iteratively corrects and re-embeds text is able to recover 92% of 32-token text inputs exactly. We train our model to decode text embeddings from two state-of-the-art embedding models, and also show that our model can recover important personal information (full names) from a dataset of clinical notes.- Anthology ID:
- 2023.emnlp-main.765
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 12448–12460
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.765
- DOI:
- 10.18653/v1/2023.emnlp-main.765
- Cite (ACL):
- John Morris, Volodymyr Kuleshov, Vitaly Shmatikov, and Alexander Rush. 2023. Text Embeddings Reveal (Almost) As Much As Text. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 12448–12460, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Text Embeddings Reveal (Almost) As Much As Text (Morris et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2023.emnlp-main.765.pdf