Neurosymbolic Characterization for Reliable Access Control Policy Analysis

2025-10-23 · Adarsh Vatsa, Bethel Hall, William Eiers arxiv

Access control policies are reliability-critical configuration artifacts in cloud systems, yet administrators frequently struggle to verify that a policy permits exactly what they intend. This verification gap cannot be remedied by using LLMs to synthesize policies: we find that reasoning and non-reasoning LLMs fluently explain policy behavior but cannot reason about policy semantics with reliability-grade precision, even when the specification is the LLM's own explanation. We formulate this impasse as the Verifiable Synthesis Paradox: the verification gap persists regardless of how the policy was authored. To remedy this, we introduce PolicySummarizer, a neurosymbolic tool that pairs finite-state automata with an LLM-based simplification to generate precise human-readable characterizations of requests allowed by a policy. PolicySummarizer uses model counting to guarantee the fidelity of the generated characterization by rejecting characterizations that fall below a user-configured threshold in favor of the formally derived one. On 546 AWS, 100 Microsoft Azure, and 100 Google Cloud Platform policies, PolicySummarizer achieves a mean similarity score of 0.93 and a 2.7x improvement over an SMT-based baseline. In a user study, PolicySummarizer raised policy-change-review accuracy from 39% to 93% on the hardest sub-task while reducing self-reported mental demand. We release PolicySummarizer as an open-source tool.

📄 PDF Abstract BibTeX arXiv:2510.20692

Code (0)

등록된 구현이 없습니다.

SoK: Access Control Policy Generation from High-level Natural Language Requirements

2023-10-05 · Sakuna Harinda Jayasundara, Nalin Asanka Gamagedara Arachchilage, Giovanni Russello

Administrator-centered access control failures can cause data breaches, putting organizations at risk of financial loss and reputation damage. Existing graphical policy configuration tools and automated policy generation…

Systematic Literature Review

Neurosymbolic Transformers for Multi-Agent Communication

2021-01-05 · NeurIPS 2020 12 · Jeevana Priya Inala, Yichen Yang, James Paulos, Yewen Pu 외

We study the problem of inferring communication structures that can solve cooperative multi-agent planning problems while minimizing the amount of communication. We quantify the amount of communication as the maximum deg…

RAGent: Retrieval-based Access Control Policy Generation

2024-09-08 · Sakuna Harinda Jayasundara, Nalin Asanka Gamagedara Arachchilage, Giovanni Russello

Manually generating access control policies from an organization's high-level requirement specifications poses significant challenges. It requires laborious efforts to sift through multiple documents containing such spec…

Domain Adaptation Retrieval Retrieval-augmented Generation

Neurosymbolic Reinforcement Learning with Formally Verified Exploration

2020-09-26 · NeurIPS 2020 12 · Greg Anderson, Abhinav Verma, Isil Dillig, Swarat Chaudhuri

We present Revel, a partially neural reinforcement learning (RL) framework for provably safe exploration in continuous state and action spaces. A key challenge for provably safe deep RL is that repeatedly verifying neura…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Safe Exploration

Neurosymbolic Reinforcement Learning and Planning: A Survey

2023-09-02 · K. Acharya, W. Raza, C. M. J. M. Dourado Jr, A. Velasquez 외

The area of Neurosymbolic Artificial Intelligence (Neurosymbolic AI) is rapidly developing and has become a popular research topic, encompassing sub-fields such as Neurosymbolic Deep Learning (Neurosymbolic DL) and Neuro…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Survey