Privacy Protection for LLM Agents

LLM: Large Language Model

Follow this topic Ask about this topic

Latest papers

29 papers6 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Oct 13, 2026

AgentCIScope: Grounded Contextual Integrity Evaluation for LLM Agents

LLM agents are becoming increasingly capable of handling daily workspace tasks by interacting with application environments through tool calls. However, as agents read and write sensitive user data across email, documents, and other applications, a central privacy question is whether they preserve contextual integrity (CI), that is, whether the information flows they produce comply with context-specific disclosure constraints. Existing work either focuses on model-level privacy leakage or evaluates agents in limited application environments with manually constructed disclosure constraints. In this work, we introduce AgentCIScope, a unified platform and benchmark for evaluating agent-level contextual integrity through executable, multi-step tasks across diverse, realistic application environments. AgentCIScope transforms public and synthetic privacy cases into executable agent tasks, with disclosure constraints grounded in three criteria: governing privacy policies, persona-based agreement, and a predefined sensitive-attribute taxonomy. Based on AgentCIScope, we evaluate 12 agents on 936 tasks and find that strong task-completion capability does not guarantee contextual-integrity preservation: single-run leakage rates range from 32.5% to 94.4%, while repeating each task five times further increases leakage by 4-19 percentage points. Leakage varies substantially across attributes: personal preferences and booking details have average leakage rates of 84.7% and 76.5%, compared with 17.1% for credit-card information and 29.4% for SSNs; environments: calendar has the highest average leakage rate as an information source, while WhatsApp ranks highest as an information destination; and governing privacy policies. AgentCIScope provides deep insights into agent privacy leakage and serves as a unified testbed for developing privacy-preserving agents.

Chengquan Guo, Zhaorun Chen, Zinan Lin +2

University of Chicago · Microsoft Research · University of Illinois Urbana-Champaign

Privacy Protection for LLM Agents Contextual Integrity LLM Agent Evaluation LLM Agent Security AI Agent Security Benchmarks

Oct 13, 2026

Cost-Efficient Privacy Enforcement for Email-Generating LLM Agents under Strategic Information Requests

LLM agents now act as delegated communication intermediaries: they read private context, draft messages, and send externally visible emails on behalf of a user. Existing checker-repair defenses can reduce inappropriate disclosure, but they rely on repeated calls to a remote action LLM (the model that drafts and repairs the email) and a remote checker LLM whenever a draft fails validation. This creates a cost problem as well as a privacy problem, especially when a requester strategically asks for exact values, raw records, source evidence, or other details that induce leakage-heavy drafts. We propose local contract-conditioned rewriting as a cost-efficient enforcement layer for email-generating agents. The mechanism intercepts an outgoing draft, constructs an information-release contract that specifies what to preserve, generalize, and forbid, rewrites the draft with a local Gemma rewriter, and selectively invokes a final PrivacyChecker. Across extensive email tasks under normal prompts and attack prompts that operationalize strategic information requests, Gemma + Checker reduces normal-prompt leakage from 11.41% to 4.03% while improving UsableRate (satisfied or partially satisfied outputs) from 85.2% to 92.6%. Under the strategic attack-prompt condition, it reduces leakage from 28.19% to 18.79% and reduces checker-only cost amplification from 1.32x to 1.02x. Offline replay ablation shows that the full contract reduces leakage relative to generic Gemma rewriting by 36.3% under normal prompts and 54.1% under attack prompts. These results support a local-first privacy enforcement design: move repair to a cheaper trusted local layer when possible, but retain the checker as the final semantic gate for high-risk sends.

Qikun Cai, Tao Huang, Chen Hou

Privacy Protection for LLM Agents LLM Agent Security Privacy Leakage in Language Models Privacy-Preserving Language Models Text Generation

Oct 1, 2026

OverAct: Measuring and Mitigating Proactive Over-Authorization in LLM Tool-Calling Agents

LLM agents with tool-calling capabilities can access external services and private user data, but they may retrieve more information than a user's request explicitly requires. We study this behavior in structured tool-calling agents and term it proactive over-authorization. This setting differs from filesystem-level coding agents because the main risk is unnecessary access to private data. We introduce OverAct, a controlled benchmark spanning eight privacy-sensitive domains with deterministic, judge-free scoring, together with an interpretive decision-theoretic framework that yields three testable predictions. Across seven models from four families, all models significantly exceed authorized scope. Request specificity is the strongest predictor of severity, over-authorization grows sublinearly with tool-pool size, and decoding temperature has little effect. These patterns are consistent with a cost-asymmetry account, suggesting that over-authorization arises more from structural decision tendencies than from decoding randomness. We also propose SelfAudit, a zero-shot inference-time method that generates request-grounded justifications and filters unjustified calls before execution. Ablation shows that explicit filtering is the main driver of scope reduction. SelfAudit reduces privacy-oriented excess by 43% without oracle knowledge.

Taolin Zhang, Jiuheng Wan, Hanyu Wang +2

Hefei University of Technology · East China Normal University · Alibaba Cloud Computing

Privacy Leakage in Language Models AI Agent Security Benchmarks Tool Access Control for LLM Agents Privacy Protection for LLM Agents

Sep 28, 2026

PrivacySkills: How Privacy Guidance Shapes Source Selection in LLM Agents

While prior work has documented privacy failures in LLM agents, it remains unclear how the presentation of privacy guidance influences their choice of information sources. We introduce PrivacySkills, a controlled framework for evaluating how agents choose among acquisition pathways that provide the same task-relevant value: consulting publicly available personal information, accessing confidential sources, or interacting with the user. The evaluation framework comprises 55 synthetic tasks spanning 11 categories of personal information, with 169 associated skills that describe the available acquisition pathways. We consider privacy guidance through system-level instructions, skill-level metadata labels, or both. Separately, we vary user availability and urgency framing. With users available and no privacy guidance, agents access confidential sources in 30% of valid runs on average across five open-weight models, despite sufficient alternatives. This rate increases to 45% when users are unavailable, whereas urgency framing has no detectable effect. System-level privacy instructions alone have limited effects on confidential access, while skill-level intrusiveness labels produce a modest reduction (24% on average), but combining the two roughly halves confidential access. Our findings motivate incorporating privacy annotations into skill specifications and evaluating their effectiveness alongside system-level instructions.

Lucas Biechy, Cédric Eichler, Héber H. Arcolezi +1

Petscraft, Inria · Université Paris-Saclay · INSA CVL +3

LLM Agent Evaluation Privacy Protection for LLM Agents

Sep 28, 2026

CoSec: Benchmarking Agent Security in Communities

LLM agents operate in persistent collaborative environments involving multiple users, communities, memories, files, and tools. Community boundaries may remain fixed or evolve with changes in membership, roles, composition, and relationships. Agents must complete legitimate tasks and prevent unauthorized disclosure of protected information. Existing evaluations do not fully examine these risks in agent systems. We introduce CoSec, an executable benchmark for evaluating privacy and authorization enforcement in LLM agent systems operating within and across communities. CoSec contains 208 canonical scenarios spanning fixed and evolving boundaries, protected information belonging to the agent owner or other participants, and attacks through dialogue, environmental content, persistent memory, and composed workflows. CoSec executes complete agent systems with persistent sessions, memory, files and tools. It verifies information flows against the active authorization state using execution traces and artifacts. Across harness and model configurations, agents frequently complete benign tasks but violate privacy and authorization boundaries. Privacy behavior varies across harnesses, attack surfaces, and community states, revealing how memory, files, tools, and workflows can carry protected information beyond its authorized scope. These findings show that task utility does not imply privacy or authorization compliance and that authorization in community settings remains an unresolved security challenge for persistent LLM agents.

Hao Chen, Wenhui Dong, Ye Chen +12

Nanjing University · Xi’an Jiaotong University · Beihang University +6

LLM Agent Security AI Agent Security Benchmarks Privacy Protection for LLM Agents Tool Access Control for LLM Agents

Sep 26, 2026

Ask Without Telling: Local SLMs Consult Cloud LLMs Without Revealing Task Intent

As local small language models (SLMs) increasingly collaborate with more capable cloud large language models (LLMs), a natural privacy question arises: Can a local SLM obtain cloud LLM guidance while protecting user privacy? Existing privacy-preserving SLM-LLM frameworks primarily hide sensitive values while preserving task semantics, which can still expose what the user is trying to accomplish. For example, allocating scarce medical supplies across hospitals may signal an emerging public-health emergency, while rebalancing an investment portfolio may reveal a private investment strategy, even when names and numerical values are hidden. Recent decoy-based methods further obscure task intent by hiding the real request among alternatives, but stronger protection relies on more decoys or semantic abstraction, increasing overhead or risking utility loss. More fundamentally, existing work does not systematically characterize the components of private task intent or how each should be protected. We therefore introduce task-private consultation, which characterizes task intent through two components: task context and task operation. To the best of our knowledge, this is the first systematic study of these components and their individual and joint protection in local-cloud SLM-LLM consultation. To realize this setting, we propose PriCon, an end-to-end framework that transforms the task itself through recoverable mathematical reformulation rather than hiding it among alternatives. A local closed-loop refinement mechanism further maintains privacy and recoverability throughout consultation. Experiments on 100 tasks show that PriCon reduces cloud-side task-intent inference Hit@1 to nearly 0%, versus 93-99% under sensitive-value removal and 3-30% under decoy-based protection, while preserving cloud-assisted utility.

Yanmeng Wang, Yunxuan Li, Shilong Fan +2

Nanjing University of Posts and Telecommunications, Nanjing, 210023, China · The Chinese University of Hong Kong, Shenzhen, 518172, China

Privacy-Preserving Language Models Privacy Protection for LLM Agents Privacy Leakage in Language Models

Sep 12, 2026

Confuse the Model, Control the Flow: Understanding and Mitigating Privacy Leakage from LLM Agents with Information Flow Control

Personal AI agents built on large language models (LLMs) are increasingly given access to a user's private data and communications in order to provide personalized assistance. This access creates a persistent privacy risk: the agent must decide whether a given sensitive information should be disclosed to a particular party. Existing defenses address this by making the agent's backend LLM more privacy-preserving through stronger system prompts, training, or explicit consent-checking procedures, but this approach has a structural challenge: whenever enforcement is a judgment the LLM makes over the same conversational context an adversary controls, the enforcement mechanism and the attack surface coincide. We demonstrate this against existing defenses with three new attacks that require only ordinary agent interaction and no prompt injection: Collaborative Workspace Lure reframes an extraction attempt as collaborative work; Semantic Obfuscation Attack induces disclosure through omission rather than through anything the agent writes; and Channel Decoupling Attack splits the extraction request and the disclosure across independent channels. All three achieve substantially higher leak rates than the attacks these defenses were originally designed to withstand. Guided by this observation, we present FLOWSEAL, a defense that enforces confidentiality through a tool-level interceptor outside the LLM's context, grounded in data provenance and an information-flow-control lattice with controlled declassification. Evaluated across three benchmarks, five prompt-based baselines, and eight attacks, including a real agent executing live tool calls through MCP, FLOWSEAL reduces leak rates to near zero (e.g., 52.2% to 0.5% against Collaborative Workspace Lure) while preserving task utility, regardless of the underlying LLM backend.

Minsun Shim, Ramisha Raida Karim, Ruthwik Jakkula +4

University of California, Irvine · University of California, Santa Cruz · University of California, Davis +1

LLM Agent Security Privacy Leakage in Language Models Privacy Protection for LLM Agents Tool Access Control for LLM Agents Information Flow Control

Aug 18, 2026

Redakto - The Incognito Tab for LLMs

Large Language Models (LLMs) are being increasingly used in everyday applications. A major challenge in the context of LLMs or Artificial Intelligence (AI) in general is to ensure privacy when using them, meaning that personally identifiable information (PII) is removed from any text that enters an LLM. These challenges have become more urgent with novel EU legislation. Uncertainty around LLM usage with respect to privacy concerns in EU countries can be a major blocker for the speed of innovation and transfer from research to applications. Here we present Redakto, a tool that can be used for anonymizing text prior to feeding it to an LLM or other downstream text processing. We provide state-of-the-art functionalities for both redaction of PII but also when used for pseudonymization. These functionalities are exposed such that they can easily be used by end-users, through the Redakto web application, and by developers and researchers, via REST APIs and model context protocol (MCP) hooks. The implementation is fully open source, requires modest compute resources, and can be readily deployed on local hardware. In contrast to prior work and in order to better assess the quality of the anonymized texts, we conduct extensive empirical evaluations on textual data from legal and medical domain with respect to both privacy and utility of the redacted texts. Our empirical results demonstrate that the texts anonymized with different redaction strategies achieve utility scores on par with the original texts, suggesting that anonymization with Redakto can be used for LLM tasks without substantial negative impact for the tasks we explored.

Saurav Kumar Saha, Tom Röhr, Felix Bießmann

Berlin University of Applied Sciences, Luxemburger Str. 10, 13353 Berlin, Germany · Einstein Center Digital Future, Wilhelmstraße 67, 10117 Berlin, Germany

Privacy Protection for LLM Agents Privacy-Preserving Language Models

Aug 10, 2026

Beyond Direct Identifiers: Probabilistic Privacy Risk Estimation for Privacy-Conscious LLM Query Delegation

Recent work on protecting privacy during user-LLM interactions often focuses on direct, explicit identifiers: the personally-identifiable information (PII) captured by standard detectors. One such approach is Privacy-Conscious Delegation (PCD), where a local LLM acts as an intermediary. However, privacy risk does not stem solely from explicit identifiers but also PII-free self-disclosures, leaving users identifiable through combinations of quasi-identifying traits. We investigate a probabilistic variant of PCD, where we augment its objectives with an LLM-driven probabilistic estimation of k-anonymity. To facilitate this, we first create the PUPA-SD dataset, which contains naturalistic user queries with self-disclosure. Our preliminary results indicate that optimizing PAPILLON on PUPA-SD improves quality on unseen conversations across a variety of local models and produces the best privacy-utility balance for Llama-3.2-3B, while smaller models struggle to jointly optimize quality and privacy. We propose k-anonymity as a useful auxiliary metric for tackling PCD.

Li Siyan, Zhou Yu, Julia Hirschberg

Department of Computer Science Columbia University

Privacy-Preserving Language Models Privacy Leakage in Language Models Privacy-Preserving ML Privacy Protection for LLM Agents

Aug 3, 2026

MNC: Scope-Bound Semantic Declassification for Private LLM-Agent Communication

Multi-agent large language model (LLM) systems can expose protected state through internal messages, tool arguments, logs, and persistent memory even when their public outputs appear innocuous. Existing privacy prompts, redaction methods, and source-level access controls restrict surface content or data access, but do not specify what a legitimately informed agent should disclose or how that disclosure may be reused downstream. We introduce Minimum-Necessary Communication (MNC), a typed semantic-declassification protocol that selects a task-sufficient disclosure from an application-authored candidate family and binds it to explicit recipient, purpose, forwarding, lifetime, logging, and memory scopes. A reference monitor enforces these scopes across subsequent operations, while a history-aware extension accounts for inference risk accumulated over repeated disclosures. Controlled semantic-join, memory, probing, and longitudinal experiments show that conventional defenses can preserve protocol-level utility while exposing substantial additional inference signal. Under identical receipt text, MNC preserves authorized delivery while blocking unauthorized forwarding, logging, durable storage, and retrieval after expiration that a text-only semantic declassifier permits. Two-backbone MAGPIE executions further show that mediated disclosures propagate through subsequent planning, tool use, coordination, and memory retrieval. These results support scope-bound semantic declassification as a practical communication boundary for private LLM-agent systems.

Jinghan Xu, Longze Fan, Zeyuan Wang +2

1Nankai University, China · 2China University of Petroleum, China · 3Sun Yat-sen University, China +1

Multi-Agent LLM Systems LLM Agent Security Information Flow Control Privacy Protection for LLM Agents

Jul 23, 2026

HiMe: Real-Time Self-Hosted Personal Agent Platform for Health Insights with Wearable Devices

Traditional approaches to wearable health signal analysis, such as smartwatches, are constrained by rigid analytical frameworks and limited personalisation. The emergence of LLM agents creates a new opportunity for Personal Health Agentic Analysis, where health insights can be generated adaptively and in context. However, currently there is no open-source locally deployable platform capable of processing personal health data in real time while preserving privacy. We present HiMe, a locally deployable, privacy-first agent platform that is fully compatible with real-time health data ecosystems across a wide range of wearable devices. HiMe is guided by three design principles. The database is treated as a first-class component. Effectiveness and efficiency are jointly optimised to achieve a low-cost Pareto-optimal balance. Data are processed in real time while the user is modelled over the long term. Together, these principles make it practical for individuals to harness Personal Health Agents for continuous, personalised health monitoring for better wellbeing.

Wei Liu, Siya Qi, Linhai Zhang +2

King’s College London · The Alan Turing Institute

Privacy Protection for LLM Agents LLM Agents Wearable Health Monitoring Personal AI Agents

Jul 19, 2026

SlotGuard: Stop Oversharing Private Local Context in LLM Agent Transcri

LLM agents can leak privacy (e.g., paths, emails) and credentials (e.g., API keys) as agent observations (e.g., tool outputs, shell logs, and file reads) are appended to provider-bound transcripts. Existing placeholder redaction is brittle: it can miss embedded or cross-turn references, over-redact benign lookalikes, and destroy the structure useful for reasoning. We present SlotGuard, a local transcript boundary that can hide sensitive data while retaining agents' performance. SlotGuard rewrites structural bindings as typed, suffix-aware slots, replaces secrets with format-preserving synthetic values, links cross-turn references with a lightweight session graph, and restores raw values only inside the trusted runtime. On controlled repository-oriented agent transcripts, SlotGuard removes all 20,814 annotated structurally sensitive characters across 9,229 paths and reduces credential leakage to 0.0% across 852 planted values. It remains close to raw-transcript task success across four upstream models, while generic redaction drops to 2.5%. Transcript rewriting takes a median of 14.424~

μ

s per agent turn. The code is publicly accessible at https://github.com/illinoisdata/SlotGuard.

Haocheng Xia, Yongjoo Park

Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign.

LLM Agent Security Privacy Leakage in Language Models Privacy Protection for LLM Agents LLM Agents

Jun 28, 2026

SurrogateShield: Beyond Redaction for High-Utility, Privacy-Preserving LLM Interactions

LLM-based assistants transmit user queries verbatim to third-party API endpoints that lie outside the user's audit or control. When those queries contain personally identifiable information (PII), the data persists on remote infrastructure subject to breach, subpoena, or policy change. Placeholder redaction (the prevailing mitigation) suppresses PII at the cost of semantic coherence, producing structurally degraded queries and correspondingly degraded responses. We present SurrogateShield, a client-side proxy that substitutes detected PII with locally generated, type-consistent surrogate values prior to transmission and restores originals in the response. No real PII crosses the network boundary. Detection runs through a three-stage cascade (PatternScan, EntityTrace, and ContextGuard) covering 22 PII types and quasi-identifier combinations grounded in Sweeney's k-anonymity framework. Surrogate-to-original mappings are sealed in an AES-256-GCM encrypted per-conversation ShadowMap that never leaves the device. Evaluations on a 1,124-query corpus demonstrate that the cascade reliably detects PII, achieving an overall F1 score of 98.87%. Surrogate substitution substantially outperforms placeholder redaction in semantic utility, yielding a 13.26 pp improvement in BERTScore (roberta-large), from 81.59% to 94.85%. Within this corpus, the local pipeline restricted real PII transmission across all tested query types; in a 100-query adversarial trial, a prompted LLM adversary recovered no original values from surrogate-substituted messages.

Sherwin Vishesh Jathanna

Arizona State University Tempe, Arizona, USA

Privacy-Preserving Language Models LLM Security PII Detection Privacy Protection for LLM Agents

Jun 26, 2026

ToolPrivacyBench: Benchmarking Purpose-Bound Privacy in Tool-Using LLM Agents

Large language models (LLMs) have increasingly moved from standalone text generation systems to agents that invoke external tools, access environments, and execute multi-step tasks. However, conventional function-calling benchmarks mainly evaluate task completion and API correctness, while privacy evaluation benchmarks typically focus on final responses or privacy judgments. Neither perspective captures purpose-bound information flow across an executed multi-tool trajectory. Motivated by this limitation in current agent evaluation, ToolPrivacyBench audits whether task-private atoms are routed only to authorized tools and downstream sinks, thereby evaluating both task completion and privacy over-disclosure during tool use. The benchmark contains 2,150 cases, including 1,150 fully synthetic privacy-sensitive business workflows and 1,000 cases adapted from existing multi-tool and function-calling benchmarks. Each case is represented by a policy knowledge base. After an agent executes against mock business backends, the evaluator compares recorded tool arguments and backend audit logs with this policy knowledge base. The evaluation covers nine widely used agents to characterize purpose-bound privacy over-disclosure. The results show that successful tool execution does not imply appropriate privacy disclosure: an agent may complete a task while transmitting unnecessary private information through intermediate tool calls. ToolPrivacyBench therefore formalizes a need-to-know disclosure boundary, under which each tool should receive only the information necessary for its stated purpose, and uses trajectory-level auditing to identify privacy over-disclosure in multi-tool workflows.

Shijing Hu, Liang Liu, Zhu Meng +1

Beijing University of Posts and Telecommunications, Beijing, 100876, China · Beijing Academy of Blockchain and Edge Computing, Beijing, 100085, China

Privacy Auditing Tool-Use Evaluation LLM Agent Evaluation Privacy Leakage in Language Models Privacy Protection for LLM Agents

Jun 22, 2026

MuPPET: A Benchmark for Contextual Privacy of LLM Assistants in Multi-Party Conversations

LLM agents are increasingly deployed in multi-party environments, handling sensitive personal data on behalf of individual users, for instance in group chats. When such an agent discloses private information, it reaches every group member at once. This risk is structurally harder to control than in one-to-one settings, as every piece of private information must be appropriate for every recipient in the group. Yet all existing contextual privacy benchmarks consider only single-interlocutor settings, leaving multi-party privacy risks unmeasured. We introduce MuPPET (Multi-Party Privacy Exposure Testing), a benchmark for contextual privacy in multi-party conversations. Our experiments show that models leak substantially more in multi-party settings than one-to-one evaluations suggest. Frontier models are vulnerable, and smaller open-weights models, often preferred for local deployment with sensitive data, even more so. Existing contextual privacy defences offer only partial protection, degrade utility, and do not resolve the underlying party-tracking problem.

Elena Sofia Ruzzetti, Cornelius Emde, Sangdoo Yun +2

Parameter Lab · University of Oxford · NAVER AI Lab +1

Privacy Leakage in Language Models Privacy Protection for LLM Agents

Jun 19, 2026

PrivacyAlign: Contextual Privacy Alignment for LLM Agents

AI agents acting on behalf of users are constantly making decisions, and for users to trust their agents, those decisions must align with what they actually want. Privacy is an important alignment problem for agents: every message, post, or tool call an agent makes is a contextual judgment about what is appropriate to share, with whom, and under which conditions. Because such judgments depend on social expectations and norms, human judgment does not merely label privacy violations but also helps define them. While existing work relies on unreliable proxies for both training and evaluation, we place human judgment at the center of agentic privacy alignment. We introduce PrivacyAlign, a dataset of 1,350 samples with 3,516 detailed annotations from 599 unique annotators across diverse scenarios where current LLMs actually leak, and use it to ground both alignment training and automated evaluation in human privacy norms. Building on these annotations, we first show that conditioning LLM judges on human annotations and explanations for reference responses to the same prompt makes their judgments more reliable. We then introduce annotation-conditioned reward modeling, which uses these annotations to score new responses during RL, and show that small open-weight agents trained with this reward better align with human privacy norms, with strong gains on PrivacyAlign and existing privacy benchmarks for agents.

Manveer Singh Tamber, Abhay Puri, Marc-Etienne Brunet +3

University of Waterloo · †Work done during internship at ServiceNow AI Research · 2ServiceNow AI Research +2

Reward Modeling Privacy Leakage in Language Models LLM Agent Safety Privacy Protection for LLM Agents

Jun 8, 2026

SecureClaw: Clawing Back Control of LLM Agents

Tool-using large language model (LLM) agents face two distinct security failures: unauthorized external actions and exposure of sensitive plaintext inside the runtime before any final output check can intervene. Existing defenses usually protect one boundary, either the planner/runtime or the point where external actions are executed, and therefore do not by themselves secure both surfaces. We present SecureClaw, a dual-boundary architecture that enforces authorization in a trusted executor and keeps raw protected data outside the LLM runtime. Sensitive reads pass through a trusted gateway that replaces raw values with reference IDs. In the evaluated deployment, the gateway also provides short planning summaries that deliberately release selected information, a process called declassification. Writes that change external state follow a PREVIEW

\rightarrow

COMMIT protocol in which only a trusted executor may execute the exact request authorized by policy. The runtime can still plan over summaries and reference IDs, but cannot directly resolve the IDs into secrets or perform side effects. Across the AgentDojo, AgentLeak, and Agent Security Bench (ASB) benchmarks, SecureClaw is the only defense we evaluate in a common harness that simultaneously retains usable task utility and achieves 0% attack success rate (ASR) on ASB, 0.64% ASR on AgentDojo, and 3.23% overall leak on AgentLeak's attacked parity lane, which measures final-output and internal-relay leakage. Code is available at https://github.com/ponyyuhan/SecureClaw.

Yuhan Ma, Stefan Schmid

TU Berlin

Data Leakage LLM Agent Security Privacy Leakage in Language Models Tool Access Control for LLM Agents Privacy Protection for LLM Agents

Jun 2, 2026

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

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.

Xinyue Huang, Xiaochun Cao, Wenyuan Yang

Sun Yat-sen University

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

May 29, 2026

PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say

LLM-based agents are rapidly advancing, autonomously invoking external tools to complete multi-step tasks for users. However, agents often acquire more sensitive information than the task requires. Existing privacy benchmarks audit what the agent's response or outgoing actions disclose, but overlook the acquisition stage where data first enters the agent's context. The over-acquired information is then one careless action or one attack away from an outright leak. To assess its prevalence, we introduce PrivacyPeek, a benchmark for evaluating acquisition-stage privacy leakage of LLM-based agents, with

1{,}182

cases across

7

acquisition behaviours and

16

application domains. Specifically, Acquisition Inspection examines the agent's tool-call trajectory, both the tools it invokes and the data it receives, to detect when it acquires sensitive information beyond the task scope. Probe Elicitation then issues a follow-up probe and measures how readily an attacker could elicit sensitive information the agent acquired but did not disclose. Our experiments on 10 LLM-based agents across 4 model families show that the unnecessary acquisition of sensitive information is widespread. In addition, we observe a correlation between the task-completion capability and acquisition-stage leakage. Prompt-level defences reduce only a small fraction of acquisition-stage leakage, leaving the majority unmitigated. These results make auditing acquisition-stage privacy both urgent and necessary. Our dataset and code are available at https://github.com/Xuan269/PrivacyPeek-Resource.

Mingxuan Zhang, Jiahui Han, Dadi Guo +5

Shanghai Artificial Intelligence Laboratory · Southeast University

Data Leakage Privacy Auditing AI Agent Auditing LLM Agent Security Privacy Leakage in Language Models AI Agent Security Benchmarks+1

May 26, 2026

Got a Secret? LLM Agents Can't Keep It: Evaluating Privacy in Multi-Agent Systems

LLM safety evaluations predominantly test models in isolation, yet deployed AI agents increasingly operate within persistent social environments alongside other agents. We introduce a Moltbook-style simulation platform where thousands of LLM agents interact across communities over a simulated month, and use it to evaluate privacy as a downstream safety concern under varying degrees of social pressure. We find that shifting from single turn to multi turn social evaluation amplifies privacy violations (CIMemories 19.95% to Ours 45.30% across OpenAI models), that leakage is socially contagious, with agents 8 times more likely to disclose sensitive information after observing a peer do so, and that explicit privacy instructions reduce but do not eliminate this effect, leaving leakage rates above 37.8% even with safeguards. Our findings suggest that static chat based safety benchmarks systematically underestimate risks in agentic deployment, and that social context alone is sufficient to elicit sensitive disclosures that single turn evaluations would never surface.

Aman Priyanshu, Supriti Vijay, Esha Pahwa

Foundation AI · USA · Corvic AI

AI Agent Safety Benchmarks Multi-Agent LLM Systems LLM Agent Evaluation LLM Agent Security Privacy Leakage in Language Models Data Leakage+2

May 9, 2026

PAAC: Privacy-Aware Agentic Device-Cloud Collaboration

Large language model (LLM) agents face a structural tension: cloud agents provide strong reasoning but expose user data, while on-device agents preserve privacy at the cost of overall capability. Existing device-cloud designs treat this boundary as a compute split rather than a trust boundary suited to agentic workloads, and existing sanitizers force a choice between policy flexibility and the structural fidelity tool calls require. In this work, we develop PAAC, a privacy-aware agentic framework that aligns planner--executor decomposition with the device-cloud boundary so that role specialization itself becomes the privacy mechanism. The cloud agent reasons over typed placeholder tokens that preserve each sensitive value's reasoning role while discarding its content, while the on-device agent identifies sensitive spans and distills each step's execution outcome into compact key findings. Sanitization confines the on-device LLM to proposing which spans to mask, while a deterministic registry performs all substitution and reversal, keeping actions directly executable on device. On three agentic benchmarks under strict privacy settings, PAAC dominates the Pareto frontier of privacy and accuracy, improving average accuracy by 15-36% and reducing average leakage by 2-6

\times

over state-of-the-art device-cloud baselines, with the largest margins on privacy targets outside fixed entity taxonomies. We find consistent improvements on 17 additional benchmarks spanning 10 domains, including math, science, and finance.

Liangqi Yuan, Wenzhi Fang, Shiqiang Wang +1

1Purdue University · University of Exeter

Privacy-Preserving Language Models AI Agent Security Privacy Protection for LLM Agents LLM Agents

Apr 7, 2026

Say Something Else: Rethinking Contextual Privacy as Information Sufficiency

LLM agents increasingly draft messages on behalf of users, yet users routinely overshare sensitive information and disagree on what counts as private. Existing systems support only suppression (omitting sensitive information) and generalization (replacing information with an abstraction), and are typically evaluated on single isolated messages, leaving both the strategy space and evaluation setting incomplete. We formalize privacy-preserving LLM communication as an Information Sufficiency (IS) task, introduce free-text pseudonymization as a third strategy that replaces sensitive attributes with functionally equivalent alternatives, and propose a conversational evaluation protocol that assesses strategies under realistic multi-turn follow-up pressure. Across 792 scenarios spanning three power-relation types (institutional, peer, intimate) and three sensitivity categories (discrimination risk, social cost, boundary), we evaluate seven frontier LLMs on privacy at two granularities, covertness, and utility. Pseudonymization yields the strongest privacy\textendash utility tradeoff overall, and single-message evaluation systematically underestimates leakage, with generalization losing up to 16.3 percentage points of privacy under follow-up.

Yunze Xiao, Wenkai Li, Xiaoyuan Wu +3

Carnegie Mellon University · Massachusetts Institute of Technology · 2077AI +1

Privacy-Preserving Language Models Privacy Protection for LLM Agents Privacy Leakage in Language Models

Apr 7, 2026

BodhiPromptShield: Pre-Inference Prompt Mediation for Surface-Form Privacy Propagation in LLM Agent Pipelines

In LLM agent pipelines, prompt privacy risk propagates beyond a single model call: raw user content enters retrieval queries, memory writes, tool arguments, OCR-derived text, and logs, and every downstream copy inherits what the first write contained. Existing de-identification pipelines protect document boundaries but not this cross-stage surface. We present BodhiPromptShield, a policy-aware mediation layer that detects sensitive spans before they propagate, replaces each with a typed placeholder, a semantic abstraction, or a secure symbolic token under a configured policy, and defers restoration to authorized execution boundaries. We evaluate it under one protocol against Presidio, Casper-style sanitization, an LLM sanitizer, and transformer and learned detectors, on 300 AI4Privacy documents, 493 PrivacyLens trajectories, 200 PrivacyLens tasks scored by that benchmark's own judge, and AgentDojo tasks under injection. Three findings result. Identifier propagation is controllable: residual exposure falls to 7.4% on AI4Privacy and 1.8% on PrivacyLens, and exact identifiers in an agent's final action fall from 13.7% to 2.1-3.1%. Restoration timing governs what every stage upstream of the authorized boundary sees: deferring it leaves 1.6% of protected values readable in the released context against 51.0%, and 2.7% against 4.8% in what the agent emits, for 0.11 helpfulness points. Measuring factual disclosure is harder: a word-overlap metric and an LLM judge both report that mediation leaves facts intact, and both disagree with blind human annotation (kappa = 0.25 and 0.09). The human labels reverse that: inferability falls from 100% to 24-53% under mediation, so semantic-leakage measures need human validation before they are trusted. These are systems results on English text with open-weight models, not formal guarantees.

Bo Ma, Jinsong Wu, Weiqi Yan

Auckland University of Technology Auckland, New Zealand · Guilin University of Electronic Technology Guilin, China

Data Leakage Privacy-Preserving Language Models LLM Agent Security Privacy Leakage in Language Models PII Detection Privacy Protection for LLM Agents

Apr 1, 2026

AgentSocialBench: Evaluating Privacy Risks in Human-Centered Agentic Social Networks

With the rise of personalized, persistent LLM agent frameworks such as OpenClaw, human-centered agentic social networks in which teams of collaborative AI agents serve individual users in a social network across multiple domains are becoming a reality. This setting creates novel privacy challenges: agents must coordinate across domain boundaries, mediate between humans, and interact with other users' agents, all while protecting sensitive personal information. While prior work has evaluated multi-agent coordination and privacy preservation, the dynamics and privacy risks of human-centered agentic social networks remain unexplored. To this end, we introduce AgentSocialBench, the first benchmark to systematically evaluate privacy risk in this setting, comprising scenarios across seven categories spanning dyadic and multi-party interactions, grounded in realistic user profiles with hierarchical sensitivity labels and directed social graphs. Our experiments reveal that privacy in agentic social networks is fundamentally harder than in single-agent settings: (1) cross-domain and cross-user coordination creates persistent leakage pressure even when agents are explicitly instructed to protect information, (2) privacy instructions that teach agents how to abstract sensitive information paradoxically cause them to discuss it more (we call it abstraction paradox). These findings underscore that current LLM agents lack robust mechanisms for privacy preservation in human-centered agentic social networks, and that new approaches beyond prompt engineering are needed to make agent-mediated social coordination safe for real-world deployment.

Prince Zizhuang Wang, Shuli Jiang

Carnegie Mellon University

Privacy Protection for LLM Agents LLM Agent Security Privacy Leakage in Language Models AI Agent Safety Benchmarks Multi-Agent LLM Systems LLM Agent Evaluation

Mar 30, 2026

Privacy Guard & Token Parsimony by Prompt and Context Handling and LLM Routing

The large-scale adoption of Large Language Models (LLMs) forces a trade-off between operational cost (OpEx) and data privacy. Current routing frameworks reduce costs but ignore prompt sensitivity, exposing users and institutions to leakage risks towards third-party cloud providers. We formalise the "Inseparability Paradigm": advanced context management intrinsically coincides with privacy management. We propose a local "Privacy Guard" -- a holistic contextual observer powered by an on-premise Small Language Model (SLM) -- that performs abstractive summarisation and Automatic Prompt Optimisation (APO) to decompose prompts into focused sub-tasks, re-routing high-risk queries to Zero-Trust or NDA-covered models. This dual mechanism simultaneously eliminates sensitive inference vectors (Zero Leakage) and reduces cloud token payloads (OpEx Reduction). A LIFO-based context compacting mechanism further bounds working memory, limiting the emergent leakage surface. We validate the framework through a 2x2 benchmark (Lazy vs. Expert users; Personal vs. Institutional secrets) on a 1,000-sample dataset, achieving a 45% blended OpEx reduction, 100% redaction success on personal secrets, and -- via LLM-as-a-Judge evaluation -- an 85% preference rate for APO-compressed responses over raw baselines. Our results demonstrate that Token Parsimony and Zero Leakage are mathematically dual projections of the same contextual compression operator.

Alessio Langiu

National Research Council of Italy - Institute of Marine Sciences (CNR-ISMAR)

Privacy Protection for LLM Agents Privacy Leakage in Language Models LLM Routing LLM Context Management Privacy-Preserving Language Models LLM Inference Efficiency+1

Mar 19, 2026

Investigating In-Context Privacy Learning by Integrating User-Facing Privacy Tools into Conversational Agents

Supporting users in protecting sensitive information when using conversational agents (CAs) is crucial, as users may undervalue privacy protection due to outdated, partial, or inaccurate knowledge about privacy in CAs. Although privacy knowledge can be developed through standalone resources, it may not readily translate into practice and may remain detached from real-time contexts of use. In this study, we investigate in-context, experiential learning by examining how interactions with privacy tools during chatbot use enhance users' privacy learning. We also explore interface design features that facilitate engagement with these tools and learning about privacy by simulating ChatGPT's interface which we integrated with a just-in-time privacy notice panel. The panel intercepts messages containing sensitive information, warns users about potential sensitivity, offers protective actions, and provides FAQs about privacy in CAs. Participants used versions of the chatbot with and without the privacy panel across two task sessions designed to approximate realistic chatbot use. We qualitatively analyzed participants' pre- and post-test survey responses and think-aloud transcripts and describe findings related to (a) participants' perceptions of privacy before and after the task sessions and (b) interface design features that supported or hindered user-led protection of sensitive information. Finally, we discuss future directions for designing user-facing privacy tools in CAs that promote privacy learning and user engagement in protecting privacy in CAs.

Mohammad Hadi Nezhad, Francisco Enrique Vicente Castro, Ivon Arroyo

University of Massachusetts Amherst · New York University

Privacy Protection for LLM Agents Human-AI Interaction Conversational Agents

Mar 17, 2026

Anonymous-by-Construction: An LLM-Driven Framework for Privacy-Preserving Text

Responsible use of AI demands that we protect sensitive information without undermining the usefulness of data, an imperative that has become acute in the age of large language models. We address this challenge with an on-premise, LLM-driven substitution pipeline that anonymizes text by replacing personally identifiable information (PII) with realistic, type-consistent surrogates. Executed entirely within organizational boundaries using local LLMs, the approach prevents data egress while preserving fluency and task-relevant semantics. We conduct a systematic, multi-metric, cross-technique evaluation on the Action-Based Conversation Dataset, benchmarking against industry standards (Microsoft Presidio and Google DLP) and a state-of-the-art approach (ZSTS, in redaction-only and redaction-plus-substitution variants). Our protocol jointly measures privacy, semantic utility, and trainability under privacy via a lifecycle-ready criterion obtained by fine-tuning a compact encoder (BERT+LoRA) on sanitized text. In addition, we assess agentic Q&A performance by inserting an on-premise anonymization layer before the answering LLM and evaluating the quality of its responses. This intermediate, type-preserving substitution stage ensures that no sensitive content is exposed to third-party APIs, enabling responsible deployment of Q&A agents without compromising confidentiality. Our method attains state-of-the-art privacy, minimal topical drift, strong factual utility, and low trainability loss, outperforming rule-based approaches and named-entity recognition (NER) baselines and ZSTS variants on the combined privacy--utility--trainability frontier. These results show that local LLM substitution yields anonymized corpora that are both responsible to use and operationally valuable: safe for agentic pipelines and suitable for downstream fine-tuning with limited degradation.

Federico Albanese, Pablo Ronco, Nicolás D'Ippolito

Veritran, Buenos Aires, Argentina · University of Buenos Aires, Argentina · University of San Andrés, Buenos Aires, Argentina

Privacy-Preserving ML Privacy-Preserving Language Models Privacy Protection for LLM Agents

Mar 3, 2026

Contextualized Privacy Defense for LLM Agents

LLM agents increasingly act on users' personal information, yet existing privacy defenses remain limited in both design and adaptability. Most prior approaches rely on static or passive defenses, such as prompting and guarding. These paradigms are insufficient for supporting contextual, proactive privacy decisions in multi-step agent execution. We propose Contextualized Defense Instructing (CDI), a new privacy defense paradigm in which an instructor model generates step-specific, context-aware privacy guidance during execution, proactively shaping actions rather than merely constraining or vetoing them. Crucially, CDI is paired with an experience-driven optimization framework that trains the instructor via reinforcement learning (RL), where we convert failure trajectories with privacy violations into learning environments. We formalize baseline defenses and CDI as distinct intervention points in a canonical agent loop, and compare their privacy-helpfulness trade-offs within a unified simulation framework. Results show that our CDI consistently achieves a better balance between privacy preservation (94.2%) and helpfulness (80.6%) than baselines, with superior robustness to adversarial conditions and generalization.

Yule Wen, Yanzhe Zhang, Jianxun Lian +3

Tsinghua University · Georgia Tech · Microsoft +1

Privacy Protection for LLM Agents LLM Agent Security LLM Agent Safety LLM Agent Training

Jan 21, 2026

NeuroFilter: Activation-Based Guardrails for Privacy-Conscious LLM Agents

Agentic Large Language Models (LLMs) are models able to reason, plan, and execute tools over unstructured data. These abilities enable transformative applications in domains spanning personal assistants, financial, and legal domains, etc. While these systems can substantially improve productivity and service quality, effective agency typically requires access to sensitive personal or organizational information. However, this access introduces critical inference-time privacy risks, specifically regarding contextually appropriate information disclosure. While recent studies highlight the inability of agentic LLMs to consistently adhere to privacy norms, existing defenses often rely on auxiliary LLM-based monitors. However, these defenses are expensive and offer limited protection against attacks that are robust to semantic censorship. To contrast this background, this paper proposes a notion of privacy filters based on activation probing. We show that these filters are both computationally efficient and effective for both single-turn and multi-turn conversational settings. Furthermore, this work provides the first systematic investigation into probing model internals across a conversation trajectory, moving beyond static, single-prompt analysis to capture the evolving state of privacy-sensitive interactions, illustrating their applicability across contexts, attack styles, multiple base models, and challenging settings such as mosaic attacks, while providing nuanced insights into the nature of the discovered concepts and modular construction of probes.

Saswat Das, Ferdinando Fioretto

University of Virginia

LLM Guardrails Privacy Leakage in Language Models Privacy Protection for LLM Agents