Assuming You Knew: Fixing an Epistemic Semantics for Flow Policies Using Agentic AI

• URL: http://arxiv.org/abs/2608.00882v1
• Date: Sat, 01 Aug 2026 22:12:02 GMT
• Title: Assuming You Knew: Fixing an Epistemic Semantics for Flow Policies Using Agentic AI
• Abstract summary: This paper attempts to provide a unifying framework for high-level security requirements about flow of information in programs.<n>With aid from an agentic AI coding assistant, a corrected formalization has been machine checked in the Rocq proof assistant.<n>The simplicity and generality of the framework may help compare different policy specification styles and enforce them by leveraging existing techniques.
• Score: 1.0152838128195467
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many high-level security requirements are about the allowed flow of information in programs and are difficult to make precise because they involve selective downgrading. Notions from epistemic logic have emerged as a good approach to policy semantics but a robust general framework remains elusive. A paper appearing in CSF 2018, entitled ``Assuming You Know: Epistemic Semantics of Relational Annotations for Expressive Flow Policies'', attempted to provide a unifying framework---but the formalization was sketchy and a correction was announced during the conference presentation. With aid from an agentic AI coding assistant, a corrected formalization has been machine checked in the Rocq proof assistant. The simplicity and generality of the framework may help compare different policy specification styles and enforce them by leveraging existing techniques.

Related papers

• Automatic Red Teaming for Implicit Vulnerabilities of Text-to-Image Models [58.59008920408855]
  We propose Adversarial Probing for Implicit VulnErabilities (AdvPIE) to expose implicit vulnerabilities without requiring access to the parameters of target models.<n> AdvPIE adopts a policy agent to generate and refine implicit adversarial prompts based on the feedback from a judge agent.<n>Experiments on standard and safety-aligned T2I models show that AdvPIE1 effectively uncovers implicit vulnerabilities.
  arXiv  Detail & Related papers  (2026-09-05T13:45:09Z)
• Cryptographic certificates of validity for trustworthy AI [0.0]
  We propose cryptographic certificates of validity for agentic AI systems.<n>An agent's action can be accompanied by an independently checkable proof that it satisfies an agreed formal policy.
  arXiv  Detail & Related papers  (2026-06-22T16:42:25Z)
• Citation-Closure Retrieval and Per-Rule Attribution for Real-World Regulatory Compliance Question Answering [54.97384993676565]
  We formalize Regulatory Compliance QA with RegOps-Bench, a novel benchmark featuring an Operational Knowledge Graph derived from complex national R&D regulations.<n>RefWalk traverses cross-document citations, fuses multi-view candidates via max-based aggregation, and enforces per-rule attribution to explicitly map claims to sources.
  arXiv  Detail & Related papers  (2026-05-28T10:38:38Z)
• Trustworthy Clinical Decision Support Using Meta-Predicates and Domain-Specific Languages [0.0]
  Metapredicates assert which evidence types are permissible in any given rule.<n>System is instantiated in AnFiSA, an open-source platform for variant interpretation.
  arXiv  Detail & Related papers  (2026-04-23T04:11:44Z)
• PolicyBank: Evolving Policy Understanding for LLM Agents [51.86716874651299]
  PolicyBank maintains structured, tool-level policy insights and iteratively refines them.<n>PolicyBank closes up to 82% of the gap toward a human oracle.
  arXiv  Detail & Related papers  (2026-04-16T20:29:30Z)
• HIPO: Instruction Hierarchy via Constrained Reinforcement Learning [57.40686733111483]
  textscHIPO is a novel alignment framework that formulates HIF as a Constrained Markov Decision Process.<n>textscHIPO elevates system prompts from mere input context to strict algorithmic boundaries.
  arXiv  Detail & Related papers  (2026-03-17T06:12:41Z)
• Doc-PP: Document Policy Preservation Benchmark for Large Vision-Language Models [13.70855540464427]
  We introduce Doc-PP, a novel benchmark constructed from real-world reports requiring reasoning across heterogeneous visual and textual elements under strict non-disclosure policies.<n>Our evaluation highlights a systemic Reasoning-Induced Safety Gap: models frequently leak sensitive information when answers must be inferred through complex synthesis or aggregated across modalities.<n>We propose DVA, a structural inference framework that decouples reasoning from policy verification.
  arXiv  Detail & Related papers  (2026-01-07T13:45:39Z)
• Analyzing and Internalizing Complex Policy Documents for LLM Agents [53.14898416858099]
  Large Language Model (LLM)-based agentic systems rely on in-context policy documents encoding diverse business rules.<n>This motivates developing internalization methods that embed policy documents into model priors while preserving performance.<n>We introduce CC-Gen, an agentic benchmark generator with Controllable Complexity across four levels.
  arXiv  Detail & Related papers  (2025-10-13T16:30:07Z)
• Policy-as-Prompt: Turning AI Governance Rules into Guardrails for AI Agents [0.19336815376402716]
  We introduce a regulatory machine learning framework that converts unstructured design artifacts (like PRDs, TDDs, and code) into verifiable runtime guardrails.<n>Our Policy as Prompt method reads these documents and risk controls to build a source-linked policy tree.<n>System is built to enforce least privilege and data minimization.
  arXiv  Detail & Related papers  (2025-09-28T17:36:52Z)
• Explainable AI Systems Must Be Contestable: Here's How to Make It Happen [2.5875936082584623]
  This paper presents the first rigorous formal definition of contestability in explainable AI.<n>We introduce a modular framework of by-design and post-hoc mechanisms spanning human-centered interfaces, technical processes, and organizational architectures.<n>Our work equips practitioners with the tools to embed genuine recourse and accountability into AI systems.
  arXiv  Detail & Related papers  (2025-06-02T13:32:05Z)
• Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation [70.62656296780074]
  We propose AIDSAFE: Agentic Iterative Deliberation for Safety Reasoning, a novel data generation recipe.<n>A data refiner stage in AIDSAFE ensures high-quality outputs by eliminating repetitive, redundant, and deceptive thoughts.<n>Our evaluations demonstrate that AIDSAFE-generated CoTs achieve superior policy adherence and reasoning quality.
  arXiv  Detail & Related papers  (2025-05-27T21:34:40Z)
• An Algebraic Approach to Asymmetric Delegation and Polymorphic Label Inference (Technical Report) [3.183855005494611]
  Language-based information flow control (IFC) enables reasoning about and enforcing security policies in decentralized applications.<n>It can be difficult to use IFC labels to model certain security assumptions, such as semi-honest agents.<n>We propose a semantic framework that allows formalizing asymmetric delegation, which is partial delegation of confidentiality or integrity.
  arXiv  Detail & Related papers  (2025-04-29T05:00:17Z)
• Few-shot Policy (de)composition in Conversational Question Answering [54.259440408606515]
  We propose a neuro-symbolic framework to detect policy compliance using large language models (LLMs) in a few-shot setting.<n>We show that our approach soundly reasons about policy compliance conversations by extracting sub-questions to be answered, assigning truth values from contextual information, and explicitly producing a set of logic statements from the given policies.<n>We apply this approach to the popular PCD and conversational machine reading benchmark, ShARC, and show competitive performance with no task-specific finetuning.
  arXiv  Detail & Related papers  (2025-01-20T08:40:15Z)

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.