Pith. sign in

REVIEW 5 cited by

Text Embeddings Reveal (Almost) As Much As Text

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.06816 v1 pith:MANLWPXV submitted 2023-10-10 cs.CL cs.LG

John X. Morris , Volodymyr Kuleshov , Vitaly Shmatikov , Alexander M. Rush This is my paper
classification cs.CLcs.LG
keywords textembeddingsembeddinggithubmodelfullinformationjxmorris12
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

How much private information do text embeddings reveal about the original text? We investigate the problem of embedding \textit{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 na\"ive model conditioned on the embedding performs poorly, a multi-step method that iteratively corrects and re-embeds text is able to recover $92\%$ of $32\text{-token}$ 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. Our code is available on Github: \href{https://github.com/jxmorris12/vec2text}{github.com/jxmorris12/vec2text}.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Exploratory Retrieval-Augmented Planning For Continual Embodied Instruction Following

    cs.AI 2025-09 conditional novelty 6.0 of 10

    ExRAP couples LLM planning with a temporal knowledge-graph memory and information-based exploration, improving success and efficiency for continual embodied instruction following.

  2. Transforming Sensitive Documents into Quantitative Data: An AI-Based Preprocessing Toolchain for Structured and Privacy-Conscious Analysis

    cs.CL 2025-07 conditional novelty 6.0 of 10

    A local open-weight LLM toolchain transforms sensitive Swedish court decisions into anonymized English summaries and embeddings that retain semantic content, validated on 10,842 LVM documents and a suicide-related con...

  3. Cascade: Token-Sharded Private LLM Inference

    cs.LG 2025-07 conditional novelty 6.0 of 10

    Cascade performs LLM inference by sharding the token sequence across non-colluding nodes, claiming resistance to vocabulary-matching and learning-based reconstruction attacks while being orders of magnitude faster than SMPC.

  4. Learning Obfuscations Of LLM Embedding Sequences: Stained Glass Transform

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A learned stochastic embedding obfuscator, the Stained Glass Transform, is claimed to reduce mutual information between prompts and their server-side representations while preserving LLM utility.

  5. LAGO: Few-shot Crosslingual Embedding Inversion Attacks via Language Similarity-Aware Graph Optimization

    cs.CL 2025-05 conditional novelty 5.0 of 10

    LAGO shows that constraining alignment matrices of linguistically similar languages to be close improves few-shot cross-lingual embedding inversion accuracy over independent per-language baselines.

Pith tools