# AI Native Asset Intelligence

arXiv: https://arxiv.org/abs/2605.09115 · HTML: https://mlsanity.com/paper/2605.09115/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 37 references that are in the map.
- First posted on arXiv 9 May 2026.

## Builds on (most cited first, 15 of 15)

- [Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning](https://mlsanity.com/paper/2310.01061/) (2023)
- [ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs](https://mlsanity.com/paper/2410.12405/) (2024)
- [Efficient multi-prompt evaluation of LLMs](https://mlsanity.com/paper/2405.17202/) (2024)
- [Large Language Models for Cyber Security: A Systematic Literature Review](https://mlsanity.com/paper/2405.04760/) (2024)
- [Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs](https://mlsanity.com/paper/2509.01790/) (2025)
- [Exploit Prediction Scoring System (EPSS)](https://mlsanity.com/paper/1908.04856/) (2019)
- [CORTEX: Collaborative LLM Agents for High-Stakes Alert Triage](https://mlsanity.com/paper/2510.00311/) (2025)
- [Graph Mining for Cybersecurity: A Survey](https://mlsanity.com/paper/2304.00485/) (2023)
- [Toward Intelligent and Secure Cloud: Large Language Model Empowered Proactive Defense](https://mlsanity.com/paper/2412.21051/) (2024)
- [A Survey on Vulnerability Prioritization: Taxonomy, Metrics, and Research Challenges](https://mlsanity.com/paper/2502.11070/) (2025)
- [Sola-Visibility-ISPM: Benchmarking Agentic AI for Identity Security Posture Management Visibility](https://mlsanity.com/paper/2601.07880/) (2026)
- [Model Checking Access Control Policies: A Case Study using Google Cloud IAM](https://mlsanity.com/paper/2303.16688/) (2023)
- [Design and Implementation of an Open-Source Security Framework for Cloud Infrastructure](https://mlsanity.com/paper/2604.03331/) (2026)
- [Rethinking Software Misconfigurations in the Real World: An Empirical Study and Literature Analysis](https://mlsanity.com/paper/2412.11121/) (2024)
- [SecureCAI: Injection-Resilient LLM Assistants for Cybersecurity Operations](https://mlsanity.com/paper/2601.07835/) (2026)

## Built on by (most cited first, 2 of 2)

- [Coding Agents Aren't Enough! Evaluating an Enterprise Security Brain for Agentic Cloud Investigations](https://mlsanity.com/paper/2609.30345/) (2026)
- [Contextualization of Third-Party Cloud Security Findings](https://mlsanity.com/paper/2610.08895/) (2026)

## Abstract (arXiv)

Modern security environments generate fragmented signals across cloud resources, identities, configurations, and third-party security tools. Although AI-native security assistants improve access to this data, they remain largely reactive: users must ask the right questions and interpret disconnected findings. This does not scale in enterprise environments, where signal importance depends on exposure, exploitability, dependencies, and business context. Repeated AI queries may therefore produce unstable prioritization without a structured basis for comparing assets. This paper introduces AI-native asset intelligence, a framework that transforms heterogeneous security data into a structured intelligence layer for consistent, contextual, and proactive asset-level reasoning. The framework combines a modeling layer, representing assets, identities, relationships, controls, attack vectors, and blast-radius patterns, with a scoring layer that converts fragmented signals into a normalized measure of asset importance. The scoring system separates intrinsic exposure, based on misconfigurations and attack-vector evidence, from contextual importance, based on anomaly, blast radius, business criticality, and data criticality. AI contextualization refines severity and business/data classifications, while deterministic aggregation preserves consistency. We evaluate the scoring system on a production snapshot with 131,625 resources across 15 vendors and 178 asset types. Sensitivity analyses and ablations show that severity mappings control finding sensitivity, AI severity adjustment refines prioritization, attack-vector scoring responds to rare exploitability evidence, and contextual modulation selectively modifies exposed resources based on business or data importance. The results support AI-native asset intelligence as a foundation for stable prioritization and proactive security-posture reasoning.