No article text was recorded for this version.
embedding inversion vulnerability
Version 2 of 2115 papers178 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Information Leakage of Sentence Embeddings via Generative Embedding Inversion Attacks
- Blog: Sentence Embedding Leaks More Information than You Expect: Generative Embedding Inversion Attack to Recover the Whole Sentence
- Blog: Transferable Embedding Inversion Attack: Uncovering Privacy Risks in Text Embeddings without Model Queries
- Blog: Universal Zero-shot Embedding Inversion
- Blog: Text Embeddings Reveal (Almost) As Much As Text
- Blog: Information Leakage of Sentence Embeddings via Generative Embedding Inversion Attacks
- Blog: PrivLM-Bench: A Multi-level Privacy Evaluation Benchmark for Language Models
- Blog: Text Embedding Inversion Security for Multilingual Language Models
- Blog: RemoteRAG: A Privacy-Preserving LLM Cloud RAG Service
- Blog: Privacy in Large Language Models: Attacks, Defenses and Future Directions
- Blog: Threats to Pre-trained Language Models: Survey and Taxonomy
- Blog: Exploring the Privacy-Preserving Properties of Word Embeddings: Algorithmic Validation Study
- Blog: Invernet: An Inversion Attack Framework to Infer Fine-Tuning Datasets through Word Embeddings
- Blog: Sentence Embedding Leaks More Information than You Expect: Generative Embedding Inversion Attack to Recover the Whole Sentence
- Blog: Towards Sentence Level Inference Attack Against Pre-trained Language Models
- Blog: Transform Before You Query: A Privacy-Preserving Approach for Vector Retrieval with Embedding Space Alignment
- Blog: Privacy-Preserving Text Classification on BERT Embeddings with Homomorphic Encryption
- Blog: Understanding Privacy Risks of Embeddings Induced by Large Language Models
- Blog: Large Language Models are Easily Confused: A Quantitative Metric, Security Implications and Typological Analysis
- Blog: Mitigating Privacy Risks in LLM Embeddings from Embedding Inversion
- Blog: When Text Embedding Meets Large Language Model: A Comprehensive Survey
- Blog: Efficient Privacy-Preserving Retrieval Augmented Generation with Distance-Preserving Encryption
- Blog: An Investigation of Memorization Risk in Healthcare Foundation Models
- Blog: Against All Odds: Overcoming Typology, Script, and Language Confusion in Multilingual Embedding Inversion Attacks
- Blog: Membership Inference on Word Embedding and Beyond
- Blog: Transferable Embedding Inversion Attack: Uncovering Privacy Risks in Text Embeddings without Model Queries
- Blog: Harnessing the Universal Geometry of Embeddings
- Blog: DP-Forward: Fine-tuning and Inference on Language Models with Differential Privacy in Forward Pass
- Blog: Enhancing Human Resources through Data Science: a Case in Recruiting
- Blog: Privacy-Preserving Text Classification on BERT Embeddings with Homomorphic Encryption
- Blog: ALGEN: Few-shot Inversion Attacks on Textual Embeddings via Cross-Model Alignment and Generation
- Blog: Federated reasoning LLMs: a survey
- Blog: DP-Forward: Fine-tuning and Inference on Language Models with Differential Privacy in Forward Pass
- Blog: Harnessing the Universal Geometry of Embeddings
- Blog: Approximate Nearest Neighbor Search in High Dimensional Vector Databases: Current Research and Future Directions
- Blog: On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey
- Blog: P-Bench: A Multi-level Privacy Evaluation Benchmark for Language Models
- Blog: Synopsis: Secure and private trend inference from encrypted semantic embeddings
- Blog: Text Embeddings Reveal (Almost) As Much As Text
- Blog: Red-Teaming the Stable Diffusion Safety Filter
- Blog: Prive-HD: Privacy-Preserved Hyperdimensional Computing
- Blog: DRAG: Distilling RAG for SLMs from LLMs to Transfer Knowledge and Mitigate Hallucination via Evidence and Graph-based Distillation
- Blog: RemoteRAG: A Privacy-Preserving LLM Cloud RAG Service
- Blog: Fully Privacy-Preserving Federated Representation Learning via Secure Embedding Aggregation
- Blog: Retrieve Anything To Augment Large Language Models
- Blog: Locally Differentially Private Embedding Models in Distributed Fraud Prevention Systems
- Blog: An end-to-end framework for private DGA detection as a service
- Blog: Adaptive Differentially Private Structural Entropy Minimization for Unsupervised Social Event Detection
- Blog: Pacmann: Efficient Private Approximate Nearest Neighbor Search
- Blog: An Inversion Attack Against Obfuscated Embedding Matrix in Language Model Inference
- Blog: SAP: Privacy-Preserving Fine-Tuning on Language Models with Split-and-Privatize Framework
- Blog: Membership Inference Attacks and Privacy in Topic Modeling
- Blog: Intent Discovery for Enterprise Virtual Assistants: Applications of Utterance Embedding and Clustering to Intent Mining
- Blog: Extracted BERT Model Leaks More Information than You Think!
- Blog: Win-Win: A Privacy-Preserving Federated Framework for Dual-Target Cross-Domain Recommendation
- Blog: Federated Reconstruction: Partially Local Federated Learning
- Blog: You Can't Steal Nothing: Mitigating Prompt Leakages in LLMs via System Vectors
- Blog: Reconstruction Attack on Instance Encoding for Language Understanding
- Blog: Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learning
- Blog: Flexible Vertical Federated Learning with Heterogeneous Parties
Showing 60 of 115 papers.
History & citation
Current · Permanent link
- Reconstructing Private Text from Numerical Embedding Inversion merged into this direction (62% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_embedding_inversion_vulnerability_85ac68f7,
title = {embedding inversion vulnerability},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/embedding-inversion-vulnerability/rdr_85ac68f719d64f4a8ee2046fa0e5bae2},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_embedding_inversion_vulnerability_85ac68f7_v2,
title = {embedding inversion vulnerability},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/embedding-inversion-vulnerability/rdr_85ac68f719d64f4a8ee2046fa0e5bae2/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}