Cedar: A New Language for Expressive, Fast, Safe, and Analyzable Authorization (Extended Version)
Not on the map. Why?
Abstract (arXiv)
Cedar is a new authorization policy language designed to be ergonomic, fast, safe, and analyzable. Rather than embed authorization logic in an application's code, developers can write that logic as Cedar policies and delegate access decisions to Cedar's evaluation engine. Cedar's simple and intuitive syntax supports common authorization use-cases with readable policies, naturally leveraging concepts from role-based, attribute-based, and relation-based access control models. Cedar's policy structure enables access requests to be decided quickly. Cedar's policy validator leverages optional typing to help policy writers avoid mistakes, but not get in their way. Cedar's design has been finely balanced to allow for a sound and complete logical encoding, which enables precise policy analysis, e.g., to ensure that when refactoring a set of policies, the authorized permissions do not change. We have modeled Cedar in the Lean programming language, and used Lean's proof assistant to prove important properties of Cedar's design. We have implemented Cedar in Rust, and released it open-source. Comparing Cedar to two open-source languages, OpenFGA and Rego, we find (subjectively) that Cedar has equally or more readable policies, but (objectively) performs far better.
Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Mar 2024.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2024: 1; 2025: 5; 2026: 25.
31 papers.
Sort:
By area:
- 2025Progent: Securing AI Agents with Privilege Controlcited by 121
- 2025Enforcing Temporal Constraints for LLM Agentscited by 31
- 2026Formal Policy Enforcement for Real-World Agentic Systemscited by 31
- 2025VERINA: Benchmarking Verifiable Code Generationcited by 30
- 2025Systems Security Foundations for Agentic Computingcited by 9
- 2026Architecting Secure AI Agents: Perspectives on System-Level Defenses Against Indirect Prompt Injection Attackscited by 9
- 2026VIGIL: Runtime Enforcement of Behavioral Specifications in AI Agent Skillscited by 8
- 2024A Lean Dataset for International Math Olympiad: Small Steps towards Writing Math Proofs for Hard Problemscited by 6
- 2026Deontic Policies for Runtime Governance of Agentic AI Systemscited by 5
- 2026Trustworthy Agentic AI Requires Deterministic Architectural Boundariescited by 3
- 2026Verifiable Agentic Infrastructure: Proof-Derived Authorization for Sovereign AI Systemscited by 3
- 2026Agent Security is a Systems Problemcited by 2
19 more
- 2026AgentFlow: A Flow-Centric Policy Language and Framework for Securing LLM Agent Systemscited by 2
- 2025MiniScope: A Least Privilege Framework for Authorizing Tool Calling Agentscited by 1
- 2026Governing What You Cannot Observe: Adaptive Runtime Governance for Autonomous AI Agentscited by 1
- 2026Alignment Contracts for Agentic Security Systemscited by 1
- 2026AutoCedar: An Agentic Framework for Verifier-Guided Access Control Policy Synthesiscited by 1
- 2026Theory-Level Autoformalization: From Isolated Statements to Unified Formal Knowledge Basescited by 1
- 2026Prose2Policy (P2P): A Practical LLM Pipeline for Translating Natural-Language Access Policies into Executable Regocited by 0
- 2026Execution Envelopes: A Shared Admission Contract for Backend AI Execution Requestscited by 0
- 2026Governing Actions, Not Agents: Institutional Attestation as a Governance Model for Autonomous AI Systemscited by 0
- 2026Behavioral Governance for Autonomous AI Agents: The AgentBound Frameworkcited by 0
- 2026Stateful Governance for Concurrent Agentic Systemscited by 0
- 2026AEGIS: Preventing Cross-Domain Resource Abuse in MCPcited by 0
- 2026Five Primitives for Governing Autonomous AI Agents at Runtimecited by 0
- 2026If Agents Were Angels, No Governance Would Be Necessary: Out-of-Band Policy Enforcement at a Trusted Tool Boundarycited by 0
- 2026Versioned Transitive Dependency-Closure Binding and Operation-Time Effect Governance for Agent Skills: ClosureBoundcited by 0
- 2026Structured Decomposition for Reliable LLM-Generated Access Control Policiescited by 0
- 2026ZeroGate: Trust-Preserving Fast Paths for Governed AI Agent Runtimescited by 0
- 2026RAISE: Reinforcing Access Control Policy Synthesis in LLMs via Symbolic Evaluationcited by 0
- 2026VeriWeave Govern: Evidence-Gated Deterministic Runtime Governance for Enterprise AI Agentscited by 0
- 2026RAISE: Reinforcing Access Control Policy Synthesis in LLMs via Symbolic Evaluation27 Sep 2026
- 2026VeriWeave Govern: Evidence-Gated Deterministic Runtime Governance for Enterprise AI Agents26 Sep 2026
- 2026ZeroGate: Trust-Preserving Fast Paths for Governed AI Agent Runtimes21 Sep 2026
- 2026Structured Decomposition for Reliable LLM-Generated Access Control Policies21 Sep 2026
- 2026Versioned Transitive Dependency-Closure Binding and Operation-Time Effect Governance for Agent Skills: ClosureBound5 Sep 2026
- 2026If Agents Were Angels, No Governance Would Be Necessary: Out-of-Band Policy Enforcement at a Trusted Tool Boundary27 Aug 2026
- 2026Five Primitives for Governing Autonomous AI Agents at Runtime27 Aug 2026
- 2026AgentFlow: A Flow-Centric Policy Language and Framework for Securing LLM Agent Systems24 Aug 2026
- 2026AEGIS: Preventing Cross-Domain Resource Abuse in MCP20 Aug 2026
- 2026Stateful Governance for Concurrent Agentic Systems3 Aug 2026
- 2026Theory-Level Autoformalization: From Isolated Statements to Unified Formal Knowledge Bases14 Jul 2026
- 2026AutoCedar: An Agentic Framework for Verifier-Guided Access Control Policy Synthesis4 Jul 2026
19 more
- 2026Behavioral Governance for Autonomous AI Agents: The AgentBound Framework29 Jun 2026
- 2026VIGIL: Runtime Enforcement of Behavioral Specifications in AI Agent Skills25 Jun 2026
- 2026Governing Actions, Not Agents: Institutional Attestation as a Governance Model for Autonomous AI Systems24 Jun 2026
- 2026Deontic Policies for Runtime Governance of Agentic AI Systems17 Jun 2026
- 2026Agent Security is a Systems Problem18 May 2026
- 2026Verifiable Agentic Infrastructure: Proof-Derived Authorization for Sovereign AI Systems13 May 2026
- 2026Execution Envelopes: A Shared Admission Contract for Backend AI Execution Requests8 May 2026
- 2026Alignment Contracts for Agentic Security Systems30 Apr 2026
- 2026Governing What You Cannot Observe: Adaptive Runtime Governance for Autonomous AI Agents27 Apr 2026
- 2026Architecting Secure AI Agents: Perspectives on System-Level Defenses Against Indirect Prompt Injection Attacks31 Mar 2026
- 2026Prose2Policy (P2P): A Practical LLM Pipeline for Translating Natural-Language Access Policies into Executable Rego16 Mar 2026
- 2026Formal Policy Enforcement for Real-World Agentic Systems18 Feb 2026
- 2026Trustworthy Agentic AI Requires Deterministic Architectural Boundaries10 Feb 2026
- 2025Enforcing Temporal Constraints for LLM Agents25 Dec 2025
- 2025MiniScope: A Least Privilege Framework for Authorizing Tool Calling Agents11 Dec 2025
- 2025Systems Security Foundations for Agentic Computing1 Dec 2025
- 2025VERINA: Benchmarking Verifiable Code Generation29 May 2025
- 2025Progent: Securing AI Agents with Privilege Control16 Apr 2025
- 2024A Lean Dataset for International Math Olympiad: Small Steps towards Writing Math Proofs for Hard Problems28 Nov 2024
- 2025Progent: Securing AI Agents with Privilege Controlcited by 121
- 2025Enforcing Temporal Constraints for LLM Agentscited by 31
- 2026Formal Policy Enforcement for Real-World Agentic Systemscited by 31
- 2025Systems Security Foundations for Agentic Computingcited by 9
- 2026Architecting Secure AI Agents: Perspectives on System-Level Defenses Against Indirect Prompt Injection Attackscited by 9
- 2026VIGIL: Runtime Enforcement of Behavioral Specifications in AI Agent Skillscited by 8
- 2026Deontic Policies for Runtime Governance of Agentic AI Systemscited by 5
- 2026Trustworthy Agentic AI Requires Deterministic Architectural Boundariescited by 3
- 2026Verifiable Agentic Infrastructure: Proof-Derived Authorization for Sovereign AI Systemscited by 3
- 2026AgentFlow: A Flow-Centric Policy Language and Framework for Securing LLM Agent Systemscited by 2
- 2025MiniScope: A Least Privilege Framework for Authorizing Tool Calling Agentscited by 1
- 2026Alignment Contracts for Agentic Security Systemscited by 1
12 most cited of 16 All 16 (JSON)
- 2026AgentFlow: A Flow-Centric Policy Language and Framework for Securing LLM Agent Systems24 Aug 2026
- 2026AEGIS: Preventing Cross-Domain Resource Abuse in MCP20 Aug 2026
- 2026Stateful Governance for Concurrent Agentic Systems3 Aug 2026
- 2026AutoCedar: An Agentic Framework for Verifier-Guided Access Control Policy Synthesis4 Jul 2026
- 2026VIGIL: Runtime Enforcement of Behavioral Specifications in AI Agent Skills25 Jun 2026
- 2026Deontic Policies for Runtime Governance of Agentic AI Systems17 Jun 2026
- 2026Verifiable Agentic Infrastructure: Proof-Derived Authorization for Sovereign AI Systems13 May 2026
- 2026Execution Envelopes: A Shared Admission Contract for Backend AI Execution Requests8 May 2026
- 2026Alignment Contracts for Agentic Security Systems30 Apr 2026
- 2026Architecting Secure AI Agents: Perspectives on System-Level Defenses Against Indirect Prompt Injection Attacks31 Mar 2026
- 2026Formal Policy Enforcement for Real-World Agentic Systems18 Feb 2026
- 2026Trustworthy Agentic AI Requires Deterministic Architectural Boundaries10 Feb 2026
12 newest of 16 All 16 (JSON)
- 2025VERINA: Benchmarking Verifiable Code Generationcited by 30
- 2024A Lean Dataset for International Math Olympiad: Small Steps towards Writing Math Proofs for Hard Problemscited by 6
- 2026Agent Security is a Systems Problemcited by 2
- 2026Governing What You Cannot Observe: Adaptive Runtime Governance for Autonomous AI Agentscited by 1
- 2026Theory-Level Autoformalization: From Isolated Statements to Unified Formal Knowledge Basescited by 1
- 2026Prose2Policy (P2P): A Practical LLM Pipeline for Translating Natural-Language Access Policies into Executable Regocited by 0
- 2026Governing Actions, Not Agents: Institutional Attestation as a Governance Model for Autonomous AI Systemscited by 0
- 2026Behavioral Governance for Autonomous AI Agents: The AgentBound Frameworkcited by 0
- 2026Five Primitives for Governing Autonomous AI Agents at Runtimecited by 0
- 2026Versioned Transitive Dependency-Closure Binding and Operation-Time Effect Governance for Agent Skills: ClosureBoundcited by 0
- 2026Structured Decomposition for Reliable LLM-Generated Access Control Policiescited by 0
- 2026ZeroGate: Trust-Preserving Fast Paths for Governed AI Agent Runtimescited by 0
12 most cited of 14 All 14 (JSON)
- 2026RAISE: Reinforcing Access Control Policy Synthesis in LLMs via Symbolic Evaluation27 Sep 2026
- 2026VeriWeave Govern: Evidence-Gated Deterministic Runtime Governance for Enterprise AI Agents26 Sep 2026
- 2026ZeroGate: Trust-Preserving Fast Paths for Governed AI Agent Runtimes21 Sep 2026
- 2026Structured Decomposition for Reliable LLM-Generated Access Control Policies21 Sep 2026
- 2026Versioned Transitive Dependency-Closure Binding and Operation-Time Effect Governance for Agent Skills: ClosureBound5 Sep 2026
- 2026Five Primitives for Governing Autonomous AI Agents at Runtime27 Aug 2026
- 2026Theory-Level Autoformalization: From Isolated Statements to Unified Formal Knowledge Bases14 Jul 2026
- 2026Behavioral Governance for Autonomous AI Agents: The AgentBound Framework29 Jun 2026
- 2026Governing Actions, Not Agents: Institutional Attestation as a Governance Model for Autonomous AI Systems24 Jun 2026
- 2026Agent Security is a Systems Problem18 May 2026
- 2026Governing What You Cannot Observe: Adaptive Runtime Governance for Autonomous AI Agents27 Apr 2026
- 2026Prose2Policy (P2P): A Practical LLM Pipeline for Translating Natural-Language Access Policies into Executable Rego16 Mar 2026
12 newest of 14 All 14 (JSON)