DeepInvert uses unlabeled obfuscated embeddings to train an inversion model that recovers up to 73.5% of original tokens against ObfusLM, versus 26.2% for the previous best attack.
InvBERT: Reconstructing Text from Contextualized Word Embeddings by inverting the BERT pipeline
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Digital Humanities and Computational Literary Studies apply text mining methods to investigate literature. Such automated approaches enable quantitative studies on large corpora which would not be feasible by manual inspection alone. However, due to copyright restrictions, the availability of relevant digitized literary works is limited. Derived Text Formats (DTFs) have been proposed as a solution. Here, textual materials are transformed in such a way that copyright-critical features are removed, but that the use of certain analytical methods remains possible. Contextualized word embeddings produced by transformer-encoders (like BERT) are promising candidates for DTFs because they allow for state-of-the-art performance on various analytical tasks and, at first sight, do not disclose the original text. However, in this paper we demonstrate that under certain conditions the reconstruction of the original copyrighted text becomes feasible and its publication in the form of contextualized token representations is not safe. Our attempts to invert BERT suggest, that publishing the encoder as a black box together with the contextualized embeddings is critical, since it allows to generate data to train a decoder with a reconstruction accuracy sufficient to violate copyright laws.
citation-role summary
citation-polarity summary
fields
cs.CR 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
DeepInvert: Semi-Supervised Embedding Inversion Against Obfuscated Language Models
DeepInvert uses unlabeled obfuscated embeddings to train an inversion model that recovers up to 73.5% of original tokens against ObfusLM, versus 26.2% for the previous best attack.