Access Control

Follow this topic Ask about this topic

Access control determines which users, services, or AI agents may perform which operations on which data, supporting security, privacy, and accountability. Traditional approaches use role-based and attribute-based access control, policy languages such as Rego and Cedar, and formal analysis or testing to specify and verify permissions. Agentic systems add runtime checks for tool calls, delegation and revocation, information-flow tracking, and least-privilege scopes across workflows; benchmarks increasingly measure both policy compliance and task utility. A central challenge is enforcing authorization as context and authority change without leakage or privilege escalation, while avoiding excessive denials, latency, and loss of useful autonomy.

Latest papers

71 papers10 papers in the last four weeks, up 11% on the four weeks before. 0.1% of all new papers.

AutoCedar: An Agentic Framework for Verifier-Guided Access Control Policy Synthesis
Jul 4, 2026Adarsh Vatsa, Sachi Shome, Yingming Zhou +1LLM-Based Program Synthesis Access Control
Stevens Institute of Technology
Securing Multi-Tool AI Agent Chains With Dynamic, Real-Time Compositional Policies
Jul 3, 2026Chris Schneider, Kriti Faujdar, Philipp Schoenegger +1LLM Agent Security Information Flow Control
1Microsoft AI · 2Microsoft
A Theory of Least Autonomy in AI
Jul 3, 2026Christophe PariselAI Agent Security AI Agent Governance
Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents
Jun 25, 2026Nada Lahjouji, Ashwin Gerard ColacoPrivacy Leakage in Language Models Information Flow Control
University of California, Irvine Irvine, California, USA
Governing Actions, Not Agents: Institutional Attestation as a Governance Model for Autonomous AI Systems
Jun 24, 2026Jakob Salfeld-NebgenAI Agent Safety AI Agent Governance
GIF: Locally Sound Geometric Information Flow Control for LLMs
Jun 22, 2026Adam Storek, Nikolaus Holzer, Zhuo Zhang +1Privacy Leakage in Language Models LLM Security
Columbia University
Intent-Governed Tool Authorization for AI Agents
Jun 22, 2026Genliang Zhu, Chu WangAI Agent Security AI Agent Governance
Accentrust · Georgia Institute of Technology · University of Illinois Urbana-Champaign
Policy-aware Vector Search: A Vision for Fine Grained Access Control in Vector Databases
Jun 18, 2026Lakshmi Sahithi Yalamarthi, Primal PappachanAccess Control
Portland State University Portland, Oregon, USA
Same-Origin Policy for Agentic Browsers
Jun 12, 2026Xilong Wang, Xiaoxing Chen, Patrick Li +2Data Leakage AI Agent Security
Duke University · Stanford University · UC Berkeley
Data Flow Control: Data Safety Policies for AI Agents
Jun 4, 2026Charlie Summers, Eugene WuAI Agent Security Information Flow Control
Columbia University New York, New York, USA
Proof-Carrying Agent Actions: Model-Agnostic Runtime Governance for Heterogeneous Agent Systems
Jun 2, 2026Zexun WangAI Agent Governance Access Control
Ond Holdings Inc.
Overlaying Governance: A Compositional Authorization Framework for Delegation and Scope in Agentic AI
Jun 2, 2026Amjad Ibrahim, Yong LiAI Accountability AI Agent Security
Huawei Heisenberg Research Center Germany
Cordon-MAS: Defending RAG against Knowledge Poisoning via Information-Flow Control
May 26, 2026Zhe Yu, Wenpeng Xing, Gaolei Li +4RAG Poisoning Attacks Information Flow Control
Binjiang Institute of Zhejiang University · Zhejiang University · Shanghai Jiao Tong University +3
Silent Failures in Physical AI: A Literature Review of Runtime Action Authorization for Autonomous Systems
May 23, 2026Barak OrRobot Safety AI Safety Evaluation
STATE16
An Application-Layer Multi-Modal Covert-Channel Reference Monitor for LLM Agent Egress
May 20, 2026Alfredo MetereLLM Agent Security AI Agent Monitoring
Enclawed, LLC, California, USA
Prompts Don't Protect: Architectural Enforcement via MCP Proxy for LLM Tool Access Control
May 18, 2026Rohith UppalaLLM Agent Security AI Control
Independent Researcher
Do Coding Agents Understand Least-Privilege Authorization?
May 14, 2026Zheng Yan, Jingxiang Weng, Charles Chen +9Software Engineering Agents AI Agent Security
Evolvent AI Research Team
Verifiable Agentic Infrastructure: Proof-Derived Authorization for Sovereign AI Systems
May 13, 2026Jun He, Deying YuAI Agent Security AI Agent Governance
Language-Based Agent Control
May 13, 2026Timothy Zhou, Loris D'Antoni, Nadia PolikarpovaAI Agent Security Information Flow Control
Digital Identity for Agentic Systems: Toward a Portable Authorization Standard for Autonomous Agents
May 12, 2026Partha MadhiraAI Agent Security AI Agent Governance
Options, Not Clicks: Lattice Refinement for Consent-Driven MCP Authorization
May 12, 2026Ying Li, Yanju Chen, Peiran Wang +4MCP Security Tool-Use Authorization
University of California, Los Angeles USA · University of California, San Diego USA · University of Texas at Arlington USA +1
The Granularity Mismatch in Agent Security: Argument-Level Provenance Solves Enforcement and Isolates the LLM Reasoning Bottleneck
May 11, 2026Linfeng Fan, Ziwei Li, Yuan Tian +3LLM Agent Security Information Flow Control
Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China · King Abdullah University of Science and Technology, Thuwal, Saudi Arabia · Dongbei University of Finance and Economics, Dalian, China +1
The Authorization-Execution Gap Is a Major Safety and Security Problem in Open-World Agents
May 10, 2026Baoyuan Wu, Qingshan Liu, Adel Bibi +2Agent Failure Analysis AI Agent Security
Chinese University of Hong Kong, Shenzhen, China · Nanjing University of Posts and Telecommunications, China · University of Oxford, UK +2
MAGIQ: A Post-Quantum Multi-Agentic AI Governance System with Provable Security
May 7, 2026Sepideh Avizheh, Tushin Mallick, Alina Oprea +2AI Agent Governance Access Control
University of Calgary Calgary, Alberta, Canada · Northeastern University Boston, MA, USA
Authorization Propagation in Multi-Agent AI Systems: Identity Governance as Infrastructure
May 6, 2026Krti TallamAI Agent Governance Access Control
Kamiwaza AI
Securing the Agent: Vendor-Neutral, Multitenant Enterprise Retrieval and Tool Use
May 6, 2026Francisco Javier Arceo, Varsha Prasad NarsingLLM Agent Orchestration AI Agent Security
Red Hat AI · Boston, USA
Hybrid Inspection and Task-Based Access Control in Zero-Trust Agentic AI
May 4, 2026Majed El Helou, Benjamin Ryder, Chiara Troiani +3Cybersecurity LLM Agent Security
Cisco Systems, Switzerland
An AI Agent Execution Environment to Safeguard User Data
Apr 21, 2026Robert Stanley, Avi Verma, Lillian Tsai +2AI Agent Security Privacy Leakage in Language Models
University of California, Los Angeles · Google
ClawNet: Human-Symbiotic Agent Network for Cross-User Autonomous Cooperation
Apr 21, 2026Zhiqin Yang, Zhenyuan Zhang, Xianzhang Jia +4Multi-Agent Collaboration AI Agent Governance
Hong Kong Generative AI Research & Development Center · Hong Kong University of Science and Technology · Hong Kong Baptist University
Atomic Decision Boundaries: A Structural Requirement for Guaranteeing Execution-Time Admissibility in Autonomous Systems
Apr 19, 2026Marcelo FernandezAI Agent Governance Access Control
TraslaIA

Jul 4, 2026J/K move · Enter open · S save

AutoCedar: An Agentic Framework for Verifier-Guided Access Control Policy Synthesis

Adarsh Vatsa, Sachi Shome, Yingming Zhou, William Eiers

Stevens Institute of Technology

LLM-Based Program Synthesis Access Control

Open paper AskPDF arXiv

Large Language Models are increasingly used to turn natural-language requirements into code. In access control, that shortcut is dangerous: a generated policy can compile and read correctly while granting access that no one approved. The difficulty is not only writing policy code. It is fixing what the requirements mean before code is written, and then checking that the final policy actually satisfies that intent. We present AutoCedar, a verifier-guided system that first turns natural-language access-control requirements into a reviewed, checkable target, and then synthesizes Cedar policies against that target. AutoCedar decomposes schema and policy authoring into small intent atoms: reviewable claims about vocabulary and behavior. Once those atoms pass mechanical validation and human intent review, the model proposes a candidate policy, the verifier checks it against the approved target, and each failure is turned into a repair signal that tells the model whether to broaden, narrow, or restructure the policy without changing the target. Because the model's work is split into small problems, each grounded in reviewed intent and backed by verifier feedback, end-to-end policy authoring becomes tractable. AutoCedar converges on all 221 tasks of CedarBench, our benchmark of authorization tasks paired with executable semantic boundaries. Across three requirements-corpus case studies covering healthcare, education, and conference management, AutoCedar converts noisy prose and extracted access-control fragments into reviewed schemas, formal checks, and a globally verified Cedar policy store for each scenario.