An MCP-grounded eight-phase agent pipeline converts natural-language critical-infrastructure descriptions into source-verified knowledge graphs and schema-valid OSCAL SSP/SAR artifacts, with 0.90 CVE recall on a synthetic water-utility scenario.
Exploit Prediction Scoring System (EPSS)
5 Pith papers cite this work, alongside 14 external citations. Polarity classification is still indexing.
5
Pith papers citing it
14
external citations · OpenAlex
citation-role summary
method 1
citation-polarity summary
years
2026 5roles
method 1polarities
use method 1representative citing papers
A multi-layer uncertainty model finds that both transmission-layer and over-the-top exceptional-access architectures carry strictly higher modeled compromise risk than no-EA baselines, with risk distributions differing by architecture class under sparse evidence.
ASTRAL applies multimodal LLMs with prompt chaining and few-shot learning to synthesize CPS architectures from disparate sources, enabling adaptive threat identification and quantitative risk estimation, as supported by ablation studies and feedback from 14 cybersecurity practitioners.
A single C program is formally proven to harbor countably infinitely many distinct, CVE-assignable vulnerabilities, implying the set of all software vulnerabilities is infinite.
A framework combines network topology and vulnerability data into attack graphs via stateful traversal, shown on a Siemens PCS7 water treatment blueprint to reveal single-point failures and patching effects.
citing papers explorer
-
From Legacy Documentation to OSCAL: An MCP-Based Agent Pipeline for Threat-Informed Continuous Compliance in Critical Infrastructure
An MCP-grounded eight-phase agent pipeline converts natural-language critical-infrastructure descriptions into source-verified knowledge graphs and schema-valid OSCAL SSP/SAR artifacts, with 0.90 CVE recall on a synthetic water-utility scenario.
-
Quantifying Compromise Risk in Exceptional Access Architectures Under Sparse and Indirect Evidence
A multi-layer uncertainty model finds that both transmission-layer and over-the-top exceptional-access architectures carry strictly higher modeled compromise risk than no-EA baselines, with risk distributions differing by architecture class under sparse evidence.
-
From Incomplete Architecture to Quantified Risk: Multimodal LLM-Driven Security Assessment for Cyber-Physical Systems
ASTRAL applies multimodal LLMs with prompt chaining and few-shot learning to synthesize CPS architectures from disparate sources, enabling adaptive threat identification and quantitative risk estimation, as supported by ablation studies and feedback from 14 cybersecurity practitioners.
-
Vulnerability Abundance: A formal proof of infinite vulnerabilities in code
A single C program is formally proven to harbor countably infinitely many distinct, CVE-assignable vulnerabilities, implying the set of all software vulnerabilities is infinite.
-
An Approach to Generate Attack Graphs with a Case Study on Siemens PCS7 Blueprint for Water Treatment Plants
A framework combines network topology and vulnerability data into attack graphs via stateful traversal, shown on a Siemens PCS7 water treatment blueprint to reveal single-point failures and patching effects.