mlsanityData to 7 Oct 2026

Transferable Embedding Inversion Attack: Uncovering Privacy Risks in Text Embeddings without Model Queries

arXiv 2406.10280 ↗First posted 12 Jun 2024cs.CR cs.CL cs.LGcited by 25

Not on the map. Why?

Abstract (arXiv)

This study investigates the privacy risks associated with text embeddings, focusing on the scenario where attackers cannot access the original embedding model. Contrary to previous research requiring direct model access, we explore a more realistic threat model by developing a transfer attack method. This approach uses a surrogate model to mimic the victim model's behavior, allowing the attacker to infer sensitive information from text embeddings without direct access. Our experiments across various embedding models and a clinical dataset demonstrate that our transfer attack significantly outperforms traditional methods, revealing the potential privacy vulnerabilities in embedding technologies and emphasizing the need for enhanced security measures.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 21 of its 35 references that are in the map. First posted on arXiv 12 Jun 2024.

Builds on

21 of 35 references.

References · 21

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  5. 2017Billion-scale similarity search with GPUscited by 2,477
  6. 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
  7. 2021Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Modelscited by 462
  8. 2021Large Dual Encoders Are Generalizable Retrieverscited by 454
  9. 2014Understanding Deep Image Representations by Inverting Themcited by 399
  10. 2020Information Leakage in Embedding Modelscited by 199
  11. 2023Text Embeddings Reveal (Almost) As Much As Textcited by 189
  12. 2015Inverting Visual Representations with Convolutional Networkscited by 168
9 more
  1. 2019Thieves on Sesame Street! Model Extraction of BERT-based APIscited by 136
  2. 2023Sentence Embedding Leaks More Information than You Expect: Generative Embedding Inversion Attack to Recover the Whole Sentencecited by 81
  3. 2021High Fidelity Visualization of What Your Self-Supervised Representation Knows Aboutcited by 64
  4. 2021Model Extraction and Adversarial Transferability, Your BERT is Vulnerable!cited by 51
  5. 2022SSLGuard: A Watermarking Scheme for Self-supervised Learning Pre-trained Encoderscited by 43
  6. 2019Analyzing and Interpreting Neural Networks for NLP: A Report on the First BlackboxNLP Workshopcited by 22
  7. 2023Stealing the Decoding Algorithms of Language Modelscited by 19
  8. 2021Understanding Invariance via Feedforward Inversion of Discriminatively Trained Classifierscited by 11
  9. 2021InvBERT: Reconstructing Text from Contextualized Word Embeddings by inverting the BERT pipelinecited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 15; 2026: 10.

25 papers.

Sort:

By area:

  1. 2025Universal Zero-shot Embedding Inversioncited by 8
  2. 2025Privacy-Preserving Federated Embedding Learning for Localized Retrieval-Augmented Generationcited by 7
  3. 2025Rep2Text: Decoding Full Text from a Single LLM Token Representationcited by 7
  4. 2025ALGEN: Few-shot Inversion Attacks on Textual Embeddings using Alignment and Generationcited by 4
  5. 2026Zero2Text: Zero-Training Cross-Domain Inversion Attacks on Textual Embeddingscited by 4
  6. 2025Securing RAG: A Risk Assessment and Mitigation Frameworkcited by 3
  7. 2025On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Surveycited by 3
  8. 2025NLP Security and Ethics, in the Wildcited by 2
  9. 2025Privacy Challenges and Solutions in Retrieval-Augmented Generation-Enhanced LLMs for Healthcare Chatbots: A Review of Applications, Risks, and Future Directionscited by 2
  10. 2026Concept-Aware Privacy Mechanisms for Defending Embedding Inversion Attackscited by 2
  11. 2025LDIR: Low-Dimensional Dense and Interpretable Text Embeddings with Relative Representationscited by 1
  12. 2025LAGO: Few-shot Crosslingual Embedding Inversion Attacks via Language Similarity-Aware Graph Optimizationcited by 1
13 more
  1. 2025A Survey: Towards Privacy and Security in Mobile Large Language Modelscited by 1
  2. 2025SemCSE-Multi: Multifaceted and Decodable Embeddings for Aspect-Specific and Interpretable Scientific Domain Mappingcited by 1
  3. 2025When Embedding Models Meet: Procrustes Bounds and Applicationscited by 1
  4. 2025PrivTune: Efficient and Privacy-Preserving Fine-Tuning of Large Language Models via Device-Cloud Collaborationcited by 1
  5. 2026Hybrid privacy-aware semantic search: SVD-truncated document geometry and CKKS-encrypted query reranking under a restricted threat modelcited by 1
  6. 2026Pointing the Way, Hiding the Destination: Practical Private Dense Retrieval at Scalecited by 1
  7. 2025FedTDP: A Privacy-Preserving and Unified Framework for Trajectory Data Preparation via Federated Learningcited by 0
  8. 2026Trans-RAG: Query-Centric Vector Transformation for Secure Cross-Organizational Retrievalcited by 0
  9. 2026Vectors Are Not Neutral: Sensitive-Information Inference from Exported LLM Representations in Summarizationcited by 0
  10. 2026Privacy from Symmetry: Orthogonally Equivariant Transformers for LLM Inferencecited by 0
  11. 2026SHARD: cell-keyed residual splitting for alignment-resistant private dense retrievalcited by 0
  12. 2026Embedding Inference Attackcited by 0
  13. 2026Denoising-Aware Inversion: Revealing Privacy Risks in Noise-Protected Text Embeddingscited by 0