arXiv AI August 20, 2026 By Yubo Wang, Shujie Cui, James Bailey, Hongzhi Yin, Wenyu Liang, Min Tang, Shiyue Qin, Weiqing Wang

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

Read the original on arXiv AI →

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%.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

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 Machine Learning

Jun 18

TIGER: Inverting Transformer Gradients via Embedding-Subspace Distance Optimization

arXiv:2606. 18312v1 Announce Type: cross Abstract: Federated learning allows multiple clients to jointly train a shared model by sending gradient updates to a central server while keeping raw inputs local.

By William Kalikman, Ivo Petrov, Dimitar I. Dimitrov, Martin Vechev

llms rag efficiency safety

arXiv AI

Jun 24

Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training

arXiv:2507. 01752v4 Announce Type: replace-cross Abstract: Gradient-based optimization is the workhorse of deep learning, offering efficient and scalable training via backpropagation.

By Ismail Labiad, Mathurin Videau, Matthieu Kowalski, Marc Schoenauer, Alessandro Leite, Julia Kempe, Olivier Teytaud

llms benchmarks safety

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 AI

Jul 7

One Framework for All: Cross-Modal Membership Inference for Generative Models

arXiv:2607. 04339v1 Announce Type: cross Abstract: Large generative models across text-to-text, text-to-image, and image-to-text modalities have been shown to pose significant privacy risks.

By Dayong Ye, Tainqing Zhu, Kun Gao, Junhao Liu, Yichuan Chen, Shuai Zhou, Hengzhu Liu, Bo Liu, Wanlei Zhou

rag diffusion fine-tuning multimodal benchmarks safety

arXiv Computer Vision

6d ago

Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses

The paper "Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses" provides a comprehensive review of model inversion (MI) attacks that exploit trained deep neural networks to reconstruct private training data. It traces the evolution of MI from early machine‑learning contexts to recent DNN‑based attacks across various modalities and learning tasks, offering a detailed taxonomy and comparative analysis of both attacks and defenses. The authors also present an open‑source toolbox on GitHub to support further research in this area.

By Hao Fang, Yixiang Qiu, Hongyao Yu, Wenbo Yu, Jiawei Kong, Baoli Chong, Bin Chen, Xuan Wang, Shu-Tao Xia, Ke Xu

safety

One email a morning, machine-written

Related stories

DeepInvert: Semi-Supervised Embedding Inversion Against Obfuscated Language Models

TIGER: Inverting Transformer Gradients via Embedding-Subspace Distance Optimization

Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training

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

One Framework for All: Cross-Modal Membership Inference for Generative Models

Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses