Privacy Protection for LLM Agents

LLM: Large Language Model

Follow this topic Ask about this topic

Latest papers

42 papers13 papers in the last four weeks, up 160% on the four weeks before. 0.1% of all new papers.

Need to Know: Contextual-Integrity-Grounded Query Rewriting for Privacy-Conscious LLM Delegation
Jun 2, 2026Xinyue Huang, Xiaochun Cao, Wenyuan YangContextual Integrity Privacy-Preserving Language Models
Sun Yat-sen University
PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say
May 29, 2026Mingxuan Zhang, Jiahui Han, Dadi Guo +5Data Leakage Privacy Auditing
Shanghai Artificial Intelligence Laboratory · Southeast University
Got a Secret? LLM Agents Can't Keep It: Evaluating Privacy in Multi-Agent Systems
May 26, 2026Aman Priyanshu, Supriti Vijay, Esha PahwaAI Agent Safety Benchmarks Multi-Agent LLM Systems
Foundation AI · USA · Corvic AI
PAAC: Privacy-Aware Agentic Device-Cloud Collaboration
May 9, 2026Liangqi Yuan, Wenzhi Fang, Shiqiang Wang +1Privacy-Preserving Language Models AI Agent Security
Purdue University · University of Exeter
Say Something Else: Rethinking Contextual Privacy as Information Sufficiency
Apr 7, 2026Yunze Xiao, Wenkai Li, Xiaoyuan Wu +3Privacy-Preserving Language Models Privacy Protection for LLM Agents
Carnegie Mellon University · Massachusetts Institute of Technology · 2077AI +1
BodhiPromptShield: Pre-Inference Prompt Mediation for Surface-Form Privacy Propagation in LLM Agent Pipelines
Apr 7, 2026Bo Ma, Jinsong Wu, Weiqi YanData Leakage Privacy-Preserving Language Models
Auckland University of Technology Auckland, New Zealand · Guilin University of Electronic Technology Guilin, China
AgentSocialBench: Evaluating Privacy Risks in Human-Centered Agentic Social Networks
Apr 1, 2026Prince Zizhuang Wang, Shuli JiangPrivacy Protection for LLM Agents LLM Agent Security
Carnegie Mellon University
Privacy Guard & Token Parsimony by Prompt and Context Handling and LLM Routing
Mar 30, 2026Alessio LangiuPrivacy Protection for LLM Agents Privacy Leakage in Language Models
National Research Council of Italy - Institute of Marine Sciences (CNR-ISMAR)
Investigating In-Context Privacy Learning by Integrating User-Facing Privacy Tools into Conversational Agents
Mar 19, 2026Mohammad Hadi Nezhad, Francisco Enrique Vicente Castro, Ivon ArroyoPrivacy Protection for LLM Agents Human-AI Interaction
University of Massachusetts Amherst · New York University
Anonymous-by-Construction: An LLM-Driven Framework for Privacy-Preserving Text
Mar 17, 2026Federico Albanese, Pablo Ronco, Nicolás D'IppolitoPrivacy-Preserving ML Privacy-Preserving Language Models
Veritran, Buenos Aires, Argentina · University of Buenos Aires, Argentina · University of San Andrés, Buenos Aires, Argentina
Contextualized Privacy Defense for LLM Agents
Mar 3, 2026Yule Wen, Yanzhe Zhang, Jianxun Lian +3Privacy Protection for LLM Agents LLM Agent Security
Tsinghua University · Georgia Tech · Microsoft +1
NeuroFilter: Activation-Based Guardrails for Privacy-Conscious LLM Agents
Jan 21, 2026Saswat Das, Ferdinando FiorettoLLM Guardrails Privacy Leakage in Language Models
University of Virginia

Jun 2, 2026J/K move · Enter open · S save

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

Xinyue Huang, Xiaochun Cao, Wenyuan Yang

Sun Yat-sen University

Contextual Integrity Privacy-Preserving Language Models Privacy Protection for LLM Agents

Open paper AskPDF arXiv

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. We recast privacy preserving query rewriting under Contextual Integrity: a span should be forwarded only if it is necessary for the task. We introduce DelegateCI-Bench, the first task based Contextual Integrity benchmark for privacy-conscious delegation, comprising 3,167 samples that combine high quality synthetic data spanning 11 tasks and 20 task types, WildChat based real user queries, and a medical challenge set with dense sensitive information. Building on this benchmark, we propose a CI-guided reinforcement learning framework that converts essential and non-essential sensitive spans into verifiable optimization signals, and train a query rewriter to preserve task critical information while suppressing unnecessary sensitive disclosure. Experiments show that our learned rewriter achieves the best privacy-utility tradeoff, achieving up to +10.1 average utility over on-device baselines.