AI Bill of Materials and Beyond: Systematizing Security Assurance through the AI Risk Scanning (AIRS) Framework
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908657110745088 |
|---|---|
| author | Nathanson, Samuel Lee, Alexander Kieffer, Catherine Chen Junkin, Jared Ye, Jessica Saeed, Amir Lockhart, Melanie Fink, Russ Peterson, Elisha Watkins, Lanier |
| author_facet | Nathanson, Samuel Lee, Alexander Kieffer, Catherine Chen Junkin, Jared Ye, Jessica Saeed, Amir Lockhart, Melanie Fink, Russ Peterson, Elisha Watkins, Lanier |
| contents | Assurance for artificial intelligence (AI) systems remains fragmented across software supply-chain security, adversarial machine learning, and governance documentation. Existing transparency mechanisms - including Model Cards, Datasheets, and Software Bills of Materials (SBOMs) - advance provenance reporting but rarely provide verifiable, machine-readable evidence of model security. This paper introduces the AI Risk Scanning (AIRS) Framework, a threat-model-based, evidence-generating framework designed to operationalize AI assurance. The AIRS Framework evolved through three progressive pilot studies - Smurf (AIBOM schema design), OPAL (operational validation), and Pilot C (AIRS) - that reframed AI documentation from descriptive disclosure toward measurable, evidence-bound verification. The framework aligns its assurance fields to the MITRE ATLAS adversarial ML taxonomy and automatically produces structured artifacts capturing model integrity, packaging and serialization safety, structural adapters, and runtime behaviors. Currently, the AIRS Framework is scoped to provide model-level assurances for LLMs, but it could be expanded to include other modalities and cover system-level threats (e.g. application-layer abuses, tool-calling). A proof-of-concept on a quantized GPT-OSS-20B model demonstrates enforcement of safe loader policies, per-shard hash verification, and contamination and backdoor probes executed under controlled runtime conditions. Comparative analysis with SBOM standards of SPDX 3.0 and CycloneDX 1.6 reveals alignment on identity and evaluation metadata, but identifies critical gaps in representing AI-specific assurance fields. The AIRS Framework thus extends SBOM practice to the AI domain by coupling threat modeling with automated, auditable evidence generation, providing a principled foundation for standardized, trustworthy, and machine-verifiable AI risk documentation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_12668 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AI Bill of Materials and Beyond: Systematizing Security Assurance through the AI Risk Scanning (AIRS) Framework Nathanson, Samuel Lee, Alexander Kieffer, Catherine Chen Junkin, Jared Ye, Jessica Saeed, Amir Lockhart, Melanie Fink, Russ Peterson, Elisha Watkins, Lanier Cryptography and Security Artificial Intelligence Machine Learning D.2.4; D.4.6; I.2.6; I.2.7; K.6.5 Assurance for artificial intelligence (AI) systems remains fragmented across software supply-chain security, adversarial machine learning, and governance documentation. Existing transparency mechanisms - including Model Cards, Datasheets, and Software Bills of Materials (SBOMs) - advance provenance reporting but rarely provide verifiable, machine-readable evidence of model security. This paper introduces the AI Risk Scanning (AIRS) Framework, a threat-model-based, evidence-generating framework designed to operationalize AI assurance. The AIRS Framework evolved through three progressive pilot studies - Smurf (AIBOM schema design), OPAL (operational validation), and Pilot C (AIRS) - that reframed AI documentation from descriptive disclosure toward measurable, evidence-bound verification. The framework aligns its assurance fields to the MITRE ATLAS adversarial ML taxonomy and automatically produces structured artifacts capturing model integrity, packaging and serialization safety, structural adapters, and runtime behaviors. Currently, the AIRS Framework is scoped to provide model-level assurances for LLMs, but it could be expanded to include other modalities and cover system-level threats (e.g. application-layer abuses, tool-calling). A proof-of-concept on a quantized GPT-OSS-20B model demonstrates enforcement of safe loader policies, per-shard hash verification, and contamination and backdoor probes executed under controlled runtime conditions. Comparative analysis with SBOM standards of SPDX 3.0 and CycloneDX 1.6 reveals alignment on identity and evaluation metadata, but identifies critical gaps in representing AI-specific assurance fields. The AIRS Framework thus extends SBOM practice to the AI domain by coupling threat modeling with automated, auditable evidence generation, providing a principled foundation for standardized, trustworthy, and machine-verifiable AI risk documentation. |
| title | AI Bill of Materials and Beyond: Systematizing Security Assurance through the AI Risk Scanning (AIRS) Framework |
| topic | Cryptography and Security Artificial Intelligence Machine Learning D.2.4; D.4.6; I.2.6; I.2.7; K.6.5 |
| url | https://arxiv.org/abs/2511.12668 |