# BeamClean: Language Aware Embedding Reconstruction

arXiv: https://arxiv.org/abs/2505.13758 · HTML: https://mlsanity.com/paper/2505.13758/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 May 2025.

## Built on by (most cited first, 1 of 1)

- [Learning Obfuscations Of LLM Embedding Sequences: Stained Glass Transform](https://mlsanity.com/paper/2506.09452/) (2025)

## Abstract (arXiv)

In this work, we consider an inversion attack on the obfuscated input embeddings sent to a language model on a server, where the adversary has no access to the language model or the obfuscation mechanism and sees only the obfuscated embeddings along with the model's embedding table. We propose BeamClean, an inversion attack that jointly estimates the noise parameters and decodes token sequences by integrating a language-model prior. Against Laplacian and Gaussian obfuscation mechanisms, BeamClean always surpasses naive distance-based attacks. This work highlights the necessity for and robustness of more advanced learned, input-dependent methods.