ARPaCCino: An Agentic-RAG for Policy as Code Compliance

• URL: http://arxiv.org/abs/2507.10584v1
• Date: Fri, 11 Jul 2025 12:36:33 GMT
• Title: ARPaCCino: An Agentic-RAG for Policy as Code Compliance
• Authors: Francesco Romeo, Luigi Arena, Francesco Blefari, Francesco Aurelio Pironti, Matteo Lupinacci, Angelo Furfaro,
• Abstract summary: ARPaCCino is an agentic system that combines Large Language Models, Retrieval-Augmented-Generation, and tool-based validation.<n>It generates formal Rego rules, assesses IaC compliance, and iteratively refines the IaC configurations to ensure conformance.<n>Our results highlight the potential of agentic RAG architectures to enhance the automation, reliability, and accessibility of PaC.
• Score: 0.18472148461613155
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Policy as Code (PaC) is a paradigm that encodes security and compliance policies into machine-readable formats, enabling automated enforcement in Infrastructure as Code (IaC) environments. However, its adoption is hindered by the complexity of policy languages and the risk of misconfigurations. In this work, we present ARPaCCino, an agentic system that combines Large Language Models (LLMs), Retrieval-Augmented-Generation (RAG), and tool-based validation to automate the generation and verification of PaC rules. Given natural language descriptions of the desired policies, ARPaCCino generates formal Rego rules, assesses IaC compliance, and iteratively refines the IaC configurations to ensure conformance. Thanks to its modular agentic architecture and integration with external tools and knowledge bases, ARPaCCino supports policy validation across a wide range of technologies, including niche or emerging IaC frameworks. Experimental evaluation involving a Terraform-based case study demonstrates ARPaCCino's effectiveness in generating syntactically and semantically correct policies, identifying non-compliant infrastructures, and applying corrective modifications, even when using smaller, open-weight LLMs. Our results highlight the potential of agentic RAG architectures to enhance the automation, reliability, and accessibility of PaC workflows.

Related papers

• Adaptive Network Security Policies via Belief Aggregation and Rollout [6.671981851649331]
  We present a method for computing security policies that is scalable, offers theoretical guarantees, and adapts quickly to changes.<n>It assumes a model or simulator of the system and comprises three components: belief estimation through particle filtering, offline policy computation through aggregation, and online policy adaptation through rollout.<n>We analyze the approximation error of aggregation and show that rollout efficiently adapts policies to changes under certain conditions.
  arXiv  Detail & Related papers  (2025-07-21T00:26:53Z)
• Towards Safety and Security Testing of Cyberphysical Power Systems by Shape Validation [42.350737545269105]
  complexity of cyberphysical power systems leads to larger attack surfaces to be exploited by malicious actors.<n>We propose to meet those risks with a declarative approach to describe cyber power systems and automatically evaluate security and safety controls.
  arXiv  Detail & Related papers  (2025-06-14T12:07:44Z)
• Learning Deterministic Policies with Policy Gradients in Constrained Markov Decision Processes [59.27926064817273]
  We introduce an exploration-agnostic algorithm, called C-PG, which enjoys global last-iterate convergence guarantees under domination assumptions.<n>We empirically validate both the action-based (C-PGAE) and parameter-based (C-PGPE) variants of C-PG on constrained control tasks.
  arXiv  Detail & Related papers  (2025-06-06T10:29:05Z)
• On Automating Security Policies with Contemporary LLMs [3.47402794691087]
  In this paper, we present a framework for automating attack mitigation policy compliance through an innovative combination of in-context learning and retrieval-augmented generation (RAG)<n>Our empirical evaluation, conducted using publicly available CTI policies in STIXv2 format and Windows API documentation, demonstrates significant improvements in precision, recall, and F1-score when employing RAG compared to a non-RAG baseline.
  arXiv  Detail & Related papers  (2025-06-05T09:58:00Z)
• ETDI: Mitigating Tool Squatting and Rug Pull Attacks in Model Context Protocol (MCP) by using OAuth-Enhanced Tool Definitions and Policy-Based Access Control [0.0]
  The Model Context Protocol (MCP) plays a crucial role in extending the capabilities of Large Language Models (LLMs)<n>The standard MCP specification presents significant security vulnerabilities, notably Tool Poisoning and Rug Pull attacks.<n>This paper introduces the Enhanced Tool Definition Interface (ETDI), a security extension designed to fortify MCP.
  arXiv  Detail & Related papers  (2025-06-02T05:22:38Z)
• ARCeR: an Agentic RAG for the Automated Definition of Cyber Ranges [0.1957338076370071]
  This paper proposes ARCeR as an innovative solution for the automatic generation and deployment of Cyber Ranges.<n> ARCeR relies on the Agentic RAG paradigm, which allows it to fully exploit state-of-art AI technologies.
  arXiv  Detail & Related papers  (2025-04-16T14:53:28Z)
• Last-Iterate Global Convergence of Policy Gradients for Constrained Reinforcement Learning [62.81324245896717]
  We introduce an exploration-agnostic algorithm, called C-PG, which exhibits global last-ite convergence guarantees under (weak) gradient domination assumptions. We numerically validate our algorithms on constrained control problems, and compare them with state-of-the-art baselines.
  arXiv  Detail & Related papers  (2024-07-15T14:54:57Z)
• Securing the Open RAN Infrastructure: Exploring Vulnerabilities in Kubernetes Deployments [60.51751612363882]
  We investigate the security implications of and software-based Open Radio Access Network (RAN) systems. We highlight the presence of potential vulnerabilities and misconfigurations in the infrastructure supporting the Near Real-Time RAN Controller (RIC) cluster.
  arXiv  Detail & Related papers  (2024-05-03T07:18:45Z)
• A General Framework for Verification and Control of Dynamical Models via Certificate Synthesis [54.959571890098786]
  We provide a framework to encode system specifications and define corresponding certificates. We present an automated approach to formally synthesise controllers and certificates. Our approach contributes to the broad field of safe learning for control, exploiting the flexibility of neural networks.
  arXiv  Detail & Related papers  (2023-09-12T09:37:26Z)
• Dichotomy of Control: Separating What You Can Control from What You Cannot [129.62135987416164]
  We propose a future-conditioned supervised learning framework that separates mechanisms within a policy's control (actions) from those beyond a policy's control (environmentity) We show that DoC yields policies that are consistent with their conditioning inputs, ensuring that conditioning a learned policy on a desired high-return future outcome will correctly induce high-return behavior.
  arXiv  Detail & Related papers  (2022-10-24T17:49:56Z)
• Bounded Robustness in Reinforcement Learning via Lexicographic Objectives [54.00072722686121]
  Policy robustness in Reinforcement Learning may not be desirable at any cost. We study how policies can be maximally robust to arbitrary observational noise. We propose a robustness-inducing scheme, applicable to any policy algorithm, that trades off expected policy utility for robustness.
  arXiv  Detail & Related papers  (2022-09-30T08:53:18Z)
• A Regularized Implicit Policy for Offline Reinforcement Learning [54.7427227775581]
  offline reinforcement learning enables learning from a fixed dataset, without further interactions with the environment. We propose a framework that supports learning a flexible yet well-regularized fully-implicit policy. Experiments and ablation study on the D4RL dataset validate our framework and the effectiveness of our algorithmic designs.
  arXiv  Detail & Related papers  (2022-02-19T20:22:04Z)
• An Automatic Attribute Based Access Control Policy Extraction from Access Logs [5.142415132534397]
  An attribute-based access control (ABAC) model provides a more flexible approach for addressing the authorization needs of complex and dynamic systems. We present a methodology for automatically learning ABAC policy rules from access logs of a system to simplify the policy development process.
  arXiv  Detail & Related papers  (2020-03-16T15:08:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.