Confidential — Stefan Michaelcheck Only

A Domain-Specific Knowledge Graph for Reasoning over AI Security Threats and Defenses

2026graph constructionapplicationsystem

Samaneh Shamshiri, Mahdi Fahmideh, Junbeom Hur, Danial Javehri

SSRN Electronic Journal

https://doi.org/10.2139/ssrn.6510976OpenAlex: W7148234684
1
URLs Found
0
Internal Citations
4
Authors
usable
Abstract Quality
GPT-5.5 Abstract Analysis

Problems Identified (4)

Fragmented attack-defense evidence: Evidence-backed links between AI security attacks and defenses are fragmented, making large-scale synthesis and audit difficult.

Unsupported security-reasoning edges: Unsupported knowledge-graph edges can mislead downstream AI security reasoning.

Sparse verified defenses: Some attacks lack verified mitigating defenses in the synthesized evidence base.

Defense recommendation verification: Defense recommendations for attacks need accurate ranking and supporting evidence for verification.

Proposed Solutions (4)

AI security knowledge graph: The study presents a domain-specific AI security knowledge graph built from 780 papers on model-level attacks and defenses.

Evidence-gated ontology extraction: The study proposes an ontology-constrained extraction pipeline that chunks text, extracts typed entities and relations, and admits only sentence-supported triples while preserving contradictory claims with provenance.

Attack-Defense Alignment Score: The study introduces ADAS, measuring the fraction of attacks with at least one verified, non-conflicted mitigating defense.

Evidence-backed defense recommendation: The knowledge graph is used for defense recommendation where ranked recommendations include supporting quotes for verification.

Results (3)

Extractor outperforms IE baselines:

Fewer unsupported edges:

ADAS exceeds randomized baselines:

Research Domain

AI security knowledge graphs and attack-defense reasoning

← Back to all papers