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.

Trilemma: How Agents choose between Honesty, Confidentiality, and Task Completion
Nov 5, 2026Johannes Taraz, Abhinav Kumar, Sahar AbdelnabiLLM Agent Safety Personal AI Agents
ELLIS Institute Tübingen · MPI for Intelligent Systems · Tübingen AI Center +1
Accessed, never disclosed: Silent access to protected health information by medical artificial intelligence agents
Nov 2, 2026Jae Wang Lee, Abhirup Banerjee, Yeong Chan LeeMedical AI Agents Privacy Protection for LLM Agents
Department of Software, College of Computing and Informatics, Ajou University, Suwon, Republic of Korea · Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, OX3 7DQ, United Kingdom · Department of Physiology, Ajou University School of Medicine, Suwon, Republic of Korea
When Safety Checks Become Privacy Risks: A Privacy-Preserving Paradigm for LLM Agent Safety Auditing
Oct 30, 2026Yixiang Luo, Ziheng Ma, Ke Chang +2AI Agent Auditing Privacy Protection for LLM Agents
Beijing Jiaotong University, Beijing, China
P-ContextBench: From Personal Fact Recall to Personalized Agent Behavior
Oct 29, 2026Grant Nasir Brown, Abdul Basir Bari, Anmol Tadikonda +1LLM Agent Evaluation AI Agent Safety Benchmarks
Department of Computer Science, San Francisco State University
Judging Before Propagation: Task-Graph Contextual Integrity for Multi-Agent Privacy
Oct 29, 2026Hengyu Wu, Blaise Delattre, Yang CaoPrivacy Protection for LLM Agents Contextual Integrity
Department of Computer Science, School of Computing, Institute of Science Tokyo
PrivacyFlow: Privacy in AI Agents through Information Flow Analysis and Consequence-Aware Risk Management
Oct 29, 2026Robin Staab, Tom Wollschläger, Vahab Mirrokni +1Privacy Protection for LLM Agents Contextual Integrity
Google Research · ETH Zurich
InferPriv: Evaluating Inferential Privacy Leakage in LLM Assistants
Oct 25, 2026Pengrun Huang, Yiwei Fu, Luoxi Meng +1Privacy Leakage in Language Models Privacy Protection for LLM Agents
UC San Diego · University of Illinois Urbana-Champaign
Agent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM Systems
Oct 21, 2026Daniel Ruiz, Luca Luceri, Emilio FerraraLLM Agent Security Privacy Leakage in Language Models
Information Sciences Institute University of Southern California Los Angeles, CA, USA
Disclosure Begets Disclosure: A Self-Reinforcing Privacy Loop in LLM Agents with Persistent Memory
Oct 20, 2026Masahiro Kaneko, Hiromi Arai, Timothy BaldwinLLM Agent Security Privacy Protection for LLM Agents
MBZUAI · Third Intelligence · RIKEN AIP
Whose Credential Is It? How Owner Attribution in Agent MemoryShapes Cross-User Account Misuse
Oct 19, 2026Hau-Sing So, Daixian Liu, Carl Hou +3AI Agent Security LLM Agent Memory
University of Macau · Tsinghua University · Lanzhou University +2
Indistinguishable Agents: Training Agent Privacy as Twin-World Indistinguishability
Oct 18, 2026Jiaming He, Guanyu Hou, Yi Yu +1Privacy Protection for LLM Agents LLM Agent Training
Nanyang Technological University, Singapore · The University of Manchester, United Kingdom · Jilin University, China
Teaching Code Agents to Ask Without Leaking Private Code
Oct 17, 2026Wenjia Jiang, Jieke Shi, Zhensu Sun +9AI Coding Agents Privacy Protection for LLM Agents
Singapore Management University · University of Alberta · Alberta Machine Intelligence Institute (Amii) +6
SPIDES: Information-Flow Control for Browser Agents
Oct 16, 2026Egor Zverev, Juhee Kim, Leon Trampert +4LLM Agent Security Information Flow Control
ISTA · Microsoft · CISPA Helmholtz Center for Information Security
AgentCIScope: Grounded Contextual Integrity Evaluation for LLM Agents
Oct 13, 2026Chengquan Guo, Zhaorun Chen, Zinan Lin +2Privacy Protection for LLM Agents Contextual Integrity
University of Chicago · Microsoft Research · University of Illinois Urbana-Champaign
Cost-Efficient Privacy Enforcement for Email-Generating LLM Agents under Strategic Information Requests
Oct 13, 2026Qikun Cai, Tao Huang, Chen HouPrivacy Protection for LLM Agents LLM Agent Security
OverAct: Measuring and Mitigating Proactive Over-Authorization in LLM Tool-Calling Agents
Oct 1, 2026Taolin Zhang, Jiuheng Wan, Hanyu Wang +2Privacy Leakage in Language Models AI Agent Security Benchmarks
Hefei University of Technology · East China Normal University · Alibaba Cloud Computing
PrivacySkills: How Privacy Guidance Shapes Source Selection in LLM Agents
Sep 28, 2026Lucas Biechy, Cédric Eichler, Héber H. Arcolezi +1LLM Agent Evaluation Privacy Protection for LLM Agents
Petscraft, Inria · Université Paris-Saclay · INSA CVL +3
CoSec: Benchmarking Agent Security in Communities
Sep 28, 2026Hao Chen, Wenhui Dong, Ye Chen +12LLM Agent Security AI Agent Security Benchmarks
Nanjing University · Xi’an Jiaotong University · Beihang University +6
Ask Without Telling: Local SLMs Consult Cloud LLMs Without Revealing Task Intent
Sep 26, 2026Yanmeng Wang, Yunxuan Li, Shilong Fan +2Privacy-Preserving Language Models Privacy Protection for LLM Agents
Nanjing University of Posts and Telecommunications, Nanjing, 210023, China · The Chinese University of Hong Kong, Shenzhen, 518172, China
Confuse the Model, Control the Flow: Understanding and Mitigating Privacy Leakage from LLM Agents with Information Flow Control
Sep 12, 2026Minsun Shim, Ramisha Raida Karim, Ruthwik Jakkula +4LLM Agent Security Privacy Leakage in Language Models
University of California, Irvine · University of California, Santa Cruz · University of California, Davis +1
Redakto - The Incognito Tab for LLMs
Aug 18, 2026Saurav Kumar Saha, Tom Röhr, Felix BießmannPrivacy Protection for LLM Agents Privacy-Preserving Language Models
Berlin University of Applied Sciences, Luxemburger Str. 10, 13353 Berlin, Germany · Einstein Center Digital Future, Wilhelmstraße 67, 10117 Berlin, Germany
Beyond Direct Identifiers: Probabilistic Privacy Risk Estimation for Privacy-Conscious LLM Query Delegation
Aug 10, 2026Li Siyan, Zhou Yu, Julia HirschbergPrivacy-Preserving Language Models Privacy Leakage in Language Models
Department of Computer Science Columbia University
MNC: Scope-Bound Semantic Declassification for Private LLM-Agent Communication
Aug 3, 2026Jinghan Xu, Longze Fan, Zeyuan Wang +2Multi-Agent LLM Systems LLM Agent Security
1Nankai University, China · 2China University of Petroleum, China · 3Sun Yat-sen University, China +1
HiMe: Real-Time Self-Hosted Personal Agent Platform for Health Insights with Wearable Devices
Jul 23, 2026Wei Liu, Siya Qi, Linhai Zhang +2Privacy Protection for LLM Agents LLM Agents
King’s College London · The Alan Turing Institute
SlotGuard: Stop Oversharing Private Local Context in LLM Agent Transcri
Jul 19, 2026Haocheng Xia, Yongjoo ParkLLM Agent Security Privacy Leakage in Language Models
Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign.
SurrogateShield: Beyond Redaction for High-Utility, Privacy-Preserving LLM Interactions
Jun 28, 2026Sherwin Vishesh JathannaPrivacy-Preserving Language Models LLM Security
Arizona State University Tempe, Arizona, USA
ToolPrivacyBench: Benchmarking Purpose-Bound Privacy in Tool-Using LLM Agents
Jun 26, 2026Shijing Hu, Liang Liu, Zhu Meng +1Privacy Auditing Tool-Use Evaluation
Beijing University of Posts and Telecommunications, Beijing, 100876, China · Beijing Academy of Blockchain and Edge Computing, Beijing, 100085, China
MuPPET: A Benchmark for Contextual Privacy of LLM Assistants in Multi-Party Conversations
Jun 22, 2026Elena Sofia Ruzzetti, Cornelius Emde, Sangdoo Yun +2Privacy Leakage in Language Models Privacy Protection for LLM Agents
Parameter Lab · University of Oxford · NAVER AI Lab +1
PrivacyAlign: Contextual Privacy Alignment for LLM Agents
Jun 19, 2026Manveer Singh Tamber, Abhay Puri, Marc-Etienne Brunet +3Reward Modeling Privacy Leakage in Language Models
University of Waterloo · †Work done during internship at ServiceNow AI Research · 2ServiceNow AI Research +2
SecureClaw: Clawing Back Control of LLM Agents
Jun 8, 2026Yuhan Ma, Stefan SchmidData Leakage LLM Agent Security
TU Berlin

Nov 5, 2026J/K move · Enter open · S save

Trilemma: How Agents choose between Honesty, Confidentiality, and Task Completion

Johannes Taraz, Abhinav Kumar, Sahar Abdelnabi

ELLIS Institute Tübingen · MPI for Intelligent Systems · Tübingen AI Center+1

LLM Agent Safety Personal AI Agents Privacy Protection for LLM Agents LLM Agent Evaluation

Open paper AskPDF arXiv

Personal AI agents often act on underspecified instructions and draw on context such as their user's messages and calendar to decide how to proceed. This context can contain private preferences that interfere with the task, with other people's interests, or with confidentiality norms. Prior work has studied deception under goal conflicts and the leakage of private information, but largely as separate problems. We study both problems together in a simulated company Slack workspace in which four employees delegate sprint staffing to personal agents. Two agents learn from private messages that their employee avoids working with a particular colleague. Because the other agents request justifications for task preferences and the only true justification is confidential, the agents cannot simultaneously remain honest, preserve confidentiality, and complete the staffing. We evaluate seven open-weight models and Claude and GPT models. Of the 135/140 open-weight agents that pursue the avoidance preference, 107 either make false claims about task fit or logistics or cite a true consideration as if it were their actual reason. In a three-model comparison, confidentiality instructions reduce disclosure of the preference from 83% (none) to 31% (medium) to 2% (strong). However, the task is often not completed anyway; in the main experiment (medium confidentiality instructions), only 16 of 70 runs end with a valid staffing. In their reasoning traces, agents frequently acknowledge evidence against their claims and still conclude that the claims are not false; they engage in motivated reasoning. Our results indicate that agents can strategically make false or misleading claims in a day-to-day task without being instructed to; the environment provides a controlled testbed for studying how agents resolve such conflicts and for developing deception monitors.