The paper investigates how privacy-preserving sanitization of user context in large language model (LLM) interactions affects downstream performance. It identifies three mechanisms—Context‑Dependent Utility, Strategic Adaptation, and Combinatorial Interplay—that explain when and how to sanitize data. Based on these insights, the authors propose an intent‑driven local protection framework using a lightweight model (Veilmind‑4B) to dynamically extract, sanitize, and restore context, achieving lower privacy leakage while maintaining higher utility than existing baselines.
By Zhenhua Liu, Zhanxu Xie, Junjie Yu, Tong Zhu, Lijun Li, Wenliang Chen
arXiv:2606. 05004v1 Announce Type: cross Abstract: With the widespread deployment of public large language models (LLMs) such as ChatGPT, protecting user prompt privacy has become an increasingly critical issue.
By Peihua Mai, Xuanrong Gao, Youlong Ding, Xianglong Du, Wei Liu, Yan Pang
The paper evaluates privacy risks in graph neural networks enhanced by large language models (LLMs). Using a five‑stage framework, the authors test six real‑world text‑attributed graph datasets with 42 model configurations and six privacy attack methods across link, label, and membership inference threats. Results show that LLM‑enhanced GNNs are more vulnerable than shallow baselines, with semantic enrichment amplifying exploitable signals, and that differential privacy can reduce risk but at a significant cost to utility.
By Longzhu He, Zelang Wen, Chaozhuo Li, Sen Su
arXiv:2607. 22695v1 Announce Type: new Abstract: Large Language Models (LLMs) are capable of generalizing human language for the completion of never-before-seen tasks, leading to widespread deployment.
By Ryan Thornton, Mir Mehedi Ahsan Pritom, Maanak Gupta
arXiv:2606. 09401v1 Announce Type: new Abstract: Recent work has applied differential privacy (DP) to adapt large language models (LLMs) for sensitive applications, offering theoretical guarantees.
By Bart{\l}omiej Marek, Lorenzo Rossi, Vincent Hanke, Xun Wang, Michael Backes, Franziska Boenisch, Adam Dziedzic
arXiv:2410. 06814v2 Announce Type: replace Abstract: Over-parameterized models are typically vulnerable to membership inference attacks, which aim to determine whether a specific sample is included in the training of a given model.
By Hengxiang Zhang, Qiang Hu, Hongxin Wei
arXiv:2606. 24623v1 Announce Type: cross Abstract: Retrieval-Augmented Generation enhances large language models by incorporating external knowledge, but deploying it in sensitive scenarios risks privacy leakage via malicious prompts.
By Yuanhe Zhao, Tianyu Zhang, Huafei Xing, Derek F. Wong, Jianbin Li, Tao Fang
arXiv:2602.06700v2 Announce Type: replace-cross
Abstract: Graph-structured data underpin a wide spectrum of modern applications, yet their multiple sensitive attributes are not isolated but deeply co...
By Ying Song, Balaji Palanisamy
arXiv:2606. 14210v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in privacy-sensitive domains, where users must balance the risk of data exposure through external APIs against the high computational cost of local deployment.
By Zixuan Gu, Xiaojun Ye, Yang Liu
arXiv:2608. 04255v1 Announce Type: cross Abstract: Graph inference over relational data can expose sensitive edge information, and this risk becomes more severe in dynamic graphs, where repeated model updates cause privacy loss to accumulate.
By Yuyang Xia, Ruixuan Liu, Li Xiong
arXiv:2601. 14660v2 Announce Type: replace-cross Abstract: Agentic Large Language Models (LLMs) are models able to reason, plan, and execute tools over unstructured data.
By Saswat Das, Ferdinando Fioretto
The paper introduces VoxPrivacy, a benchmark for assessing interactional privacy in Speech Language Models (SLMs). It evaluates models on a 32‑hour bilingual dataset across three difficulty tiers, revealing that most open‑source SLMs perform near random on conditional privacy decisions and even strong closed‑source systems struggle with proactive privacy inference. The authors also validate these findings on a real‑speech subset and show that fine‑tuning on a 4,000‑hour training set can improve privacy‑preserving capabilities while maintaining robustness.
By Yuxiang Wang, Hongyu Liu, Dekun Chen, Xueyao Zhang, Zhizheng Wu