mlsanityData to 14 Oct 2026

Can LLMs Make (Personalized) Access Control Decisions?

arXiv 2511.20284 ↗First posted 25 Nov 2025cs.CR cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Precise access control decisions are crucial for the security of both traditional applications and emerging agent-based systems. Typically, these decisions are made by users during app installation or at runtime. However, due to the increasing complexity and automation of systems, making access control decisions can impose a significant cognitive burden on users, often overwhelming them and leading to suboptimal or even arbitrary choices. To address this problem, we investigate the ability of LLMs to make dynamic, context-aware decisions aligned with users' security preferences, expressed during a lightweight setup phase. As a case study, we analyze smartphone application permission requests, given their ubiquity and users' familiarity with them. We curated a dataset comprising 307 user privacy statements (short, natural-language descriptions of user preferences) and 14,682 corresponding permission decisions, gathered from smartphone users in an online data collection. We compare these decisions with those made by two versions of LLMs that are tasked with reasoning about the app and the request context: a general model and a personalized one (which incorporates user preferences). For the latter, we also collected user feedback on 1,298 of its decisions. Our results show that LLMs generally reflect users' preferences well, agreeing with the majority decision in up to 86% of cases, and can steer users toward safer behavior. However, the results also reveal a key trade-off in personalization: while incorporating user-specific privacy preferences improves agreement with individual decisions, strict adherence to these preferences may lead to less safe outcomes, as users tend to over-permission.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 33 of its 90 references that are in the map. First posted on arXiv 25 Nov 2025.

Builds on

33 of 90 references.

References · 33

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  3. 2023BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Datasetcited by 860
  4. 2023A Survey of Hallucination in Large Foundation Modelscited by 368
  5. 2024Humans or LLMs as the Judge? A Study on Judgement Biasescited by 323
  6. 2023Preference Ranking Optimization for Human Alignmentcited by 285
  7. 2023Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theorycited by 230
  8. 2023Do LLMs exhibit human-like response biases? A case study in survey designcited by 180
  9. 2024Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantificationcited by 162
  10. 2024Does Prompt Formatting Have Any Impact on LLM Performance?cited by 141
  11. 2024IsolateGPT: An Execution Isolation Architecture for LLM-Based Agentic Systemscited by 130
  12. 2025Securing AI Agents with Information-Flow Controlcited by 121
21 more
  1. 2024Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraphcited by 105
  2. 2024Bias and Unfairness in Information Retrieval Systems: New Challenges in the LLM Eracited by 98
  3. 2024Non-Determinism of "Deterministic" LLM Settingscited by 92
  4. 2023Self-Evaluation Improves Selective Generation in Large Language Modelscited by 76
  5. 2025Reasoning about Uncertainty: Do Reasoning Models Know When They Don't Know?cited by 38
  6. 2024A Survey on Human Preference Learning for Large Language Modelscited by 24
  7. 2024Permissive Information-Flow Analysis for Large Language Modelscited by 22
  8. 2025Towards Automating Data Access Permissions in AI Agentscited by 21
  9. 2023Using LLMs to Facilitate Formal Verification of RTLcited by 18
  10. 2024Dissecting Human and LLM Preferencescited by 17
  11. 2015Android Permissions Remystified: A Field Study on Contextual Integritycited by 15
  12. 2023Information Flow Control in Machine Learning through Modular Model Architecturecited by 11
  13. 2025LLM-as-a-Judge for Privacy Evaluation? Exploring the Alignment of Human and LLM Perceptions of Privacy in Textual Datacited by 10
  14. 2017The Feasibility of Dynamically Granted Permissions: Aligning Mobile Privacy with User Preferencescited by 9
  15. 2024DePLOI: Applying NL2SQL to Synthesize and Audit Database Access Controlcited by 7
  16. 2023Can LLMs Capture Human Preferences?cited by 6
  17. 2025Say What You Mean: Natural Language Access Control with Large Language Models for Internet of Thingscited by 6
  18. 2022Toward Deep Learning Based Access Controlcited by 4
  19. 2025LMN: A Tool for Generating Machine Enforceable Policies from Natural Language Access Control Rules using LLMscited by 4
  20. 2025Can LLMs Find Bugs in Code? An Evaluation from Beginner Errors to Security Vulnerabilities in Python and C++cited by 3
  21. 2020An Android Application Risk Evaluation Framework Based on Minimum Permission Set Identificationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2025Personalizing Agent Privacy Decisions via Logical Entailmentcited by 4
  2. 2026An AI Agent Execution Environment to Safeguard User Datacited by 4
  3. 2026CIDER: A Dataset of Contextual Disclosure Boundaries for Privacy Preference Alignmentcited by 0
  4. 2026AuthGateBench: Benchmarking LLMs as Authorization Gatecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Privacy Control in Conversational LLM Platforms: A Walkthrough Study
  2. 2025Let Them Down Easy! Contextual Effects of LLM Guardrails on User Perceptions and Preferences
  3. 2026UserToolBench: A User-Profile-Hidden Benchmark for Personalized Decision Making in Tool-Use LLMs
  4. 2024Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security
  5. 2026How Well Can LLM Agents Simulate End-User Security and Privacy Attitudes and Behaviors?
  6. 2025User Behavior Analysis in Privacy Protection with Large Language Models: A Study on Privacy Preferences with Limited Data
  7. 2025Permissioned LLMs: Enforcing Access Control in Large Language Models
  8. 2025MiniScope: A Least Privilege Framework for Authorizing Tool Calling Agents