Hugging Face Trending Papers September 6, 2026

A Novel Semantic Manifold Alignment Attack against Embedding-to-Embedding Obfuscation in Privacy-Preserving LLMs

Read the original on Hugging Face Trending Papers →

The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.

arXiv AI

Jun 26

Hybrid privacy-aware semantic search: SVD-truncated document geometry and CKKS-encrypted query reranking under a restricted threat model

arXiv:2606. 26373v1 Announce Type: cross Abstract: Dense embeddings power semantic search and retrieval-augmented generation, but embedding-inversion attacks can reconstruct source text from a vector: when a vector database leaks, the documents behind it leak too.

By Sergey Kurilenko

rag efficiency benchmarks safety

arXiv Machine Learning

Aug 6

DeepInvert: Semi-Supervised Embedding Inversion Against Obfuscated Language Models

arXiv:2608. 04477v1 Announce Type: cross Abstract: Cloud-based language model services routinely process prompts containing sensitive information.

By Zhicong Huang, Cheng Hong, Tao Wei

llms rag

arXiv AI

Sep 7

Shadow Queries for Private Retrieval in Vector Databases

The paper introduces SHAQ, a defense called Shadow Query Generation that protects document embeddings in vector databases from embedding inversion attacks. SHAQ replaces direct embeddings with diverse shadow queries generated by a language model, thereby decomposing document semantics and decoupling stored embeddings from the original text. Experiments on various IR datasets show that SHAQ significantly lowers recovery rates, defends more tokens than baseline methods, and even improves retrieval utility.

By Xinguo Feng, Zhongkui Ma, Zihan Wang, Chuan Yan, Guowei Yang, Alsharif Abuadbba, Guangdong Bai

llms rag safety

arXiv Machine Learning

Jun 16

Privacy from Symmetry: Orthogonally Equivariant Transformers for LLM Inference

arXiv:2606. 16461v1 Announce Type: new Abstract: Running large language models locally is often impractical, pushing inference on sensitive text to third-party providers.

By Alexander Yukhimchuk, Andrey Shulga, Mladen Kolar, Martin Tak\'a\v{c}

llms rag fine-tuning safety

arXiv Machine Learning

Jul 3

Embedding Inference Attack

arXiv:2607. 01276v1 Announce Type: cross Abstract: Embedding models are essential components of modern Information Retrieval (IR) systems, yet they are typically hidden behind APIs.

By Cedric Fitiavana Raelijohn, S\'ebastien Gambs, Jean-Francois Rajotte

llms rag

arXiv AI

Aug 20

Denoising-Aware Inversion: Revealing Privacy Risks in Noise-Protected Text Embeddings

The paper investigates the vulnerability of Gaussian‑noised text embeddings to inversion attacks. It identifies a "Double Noise Trap" that hampers standard generative methods and introduces DAEI, a denoising‑aware pipeline that significantly outperforms existing baselines in reconstructing original text. Experiments show DAEI improves BLEU by 154% and token‑level metrics by 32–60%.

By Yubo Wang, Shujie Cui, James Bailey, Hongzhi Yin, Wenyu Liang, Min Tang, Shiyue Qin, Weiqing Wang

rag safety

One email a morning, machine-written

Related stories

Hybrid privacy-aware semantic search: SVD-truncated document geometry and CKKS-encrypted query reranking under a restricted threat model

DeepInvert: Semi-Supervised Embedding Inversion Against Obfuscated Language Models

Shadow Queries for Private Retrieval in Vector Databases

Privacy from Symmetry: Orthogonally Equivariant Transformers for LLM Inference

Embedding Inference Attack

Denoising-Aware Inversion: Revealing Privacy Risks in Noise-Protected Text Embeddings