arXiv AI June 4, 2026 By Xinyue Huang, Xiaochun Cao, Wenyuan Yang

Need to Know: Contextual-Integrity-Grounded Query Rewriting for Privacy-Conscious LLM Delegation

arXiv:2606. 04067v1 Announce Type: cross Abstract: As LLMs become increasingly woven into everyday workflows, user queries sent to cloud hosted LLMs routinely mix task-essential content with task non-essential sensitive disclosures, yet type based PII redaction is context agnostic and may raise two issues: over disclosing untyped sensitive context and over removing answer bearing spans.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jun 15

Minim: Privacy-Aware Minimal View for Agents via Trusted Local Sanitization

arXiv:2606. 13949v1 Announce Type: new Abstract: Modern LLM-powered autonomous agents increasingly rely on rich user interface (UI) state observations to achieve reliable action grounding in complex digital environments.

By Hexuan Yu, Chaoyu Zhang, Heng Jin, Shanghao Shi, Ning Zhang, Y. Thomas Hou, Wenjing Lou

llms agents efficiency safety

arXiv AI

Jun 18

TRAP: Benchmark for Task-completion and Resistance to Active Privacy-extraction

arXiv:2606. 18996v1 Announce Type: cross Abstract: Agents are increasingly deployed in document-intensive workflows where sensitive private information is not an edge case but a routine input, e.

By Moon Ye-Bin, Nam Hyeon-Woo, Baek Seong-Eun, Yejin Yeo, Tae-Hyun Oh

agents benchmarks safety

arXiv AI

Jun 4

SharedRequest: Privacy-Preserving Model-Agnostic Inference for Large Language Models

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

llms safety

arXiv AI

Jul 7

Efficient Decentralized Multi-task Dataset Valuation via Model Merging

arXiv:2607. 03346v1 Announce Type: cross Abstract: Accurate and efficient dataset valuation is essential for enabling fair and transparent data marketplaces, especially when multiple contributors provide data for training multi-task models.

By Mohammadsajad Alipour, Mohammad Mohammadi Amiri

computer-vision nlp safety

arXiv AI

Jun 26

Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents

arXiv:2606. 26627v1 Announce Type: cross Abstract: Large language model agents increasingly query databases, search document collections, call external APIs, remember past interactions, and act on a user's behalf.

By Nada Lahjouji, Ashwin Gerard Colaco

llms rag agents benchmarks safety data-engineering

arXiv AI

Jun 24

Privacy-Preserving RAG via Multi-Agent Semantic Rewriting: Achieving Confidentiality Without Compromising Contextual Fidelity

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

llms rag agents safety

Related stories

Minim: Privacy-Aware Minimal View for Agents via Trusted Local Sanitization

TRAP: Benchmark for Task-completion and Resistance to Active Privacy-extraction

SharedRequest: Privacy-Preserving Model-Agnostic Inference for Large Language Models

Efficient Decentralized Multi-task Dataset Valuation via Model Merging

Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents

Privacy-Preserving RAG via Multi-Agent Semantic Rewriting: Achieving Confidentiality Without Compromising Contextual Fidelity