将静态软件物料清单升级为能自动推理的智能安全档案，提升漏洞可利用性判断精度。
SBOMs into Agentic AIBOMs: Schema Extensions, Agentic Orchestration, and Reproducibility Evaluation
- 构建多智能体框架，实现运行时依赖与环境漂移的自主监控
- 生成结构化漏洞可利用性声明，比传统系统更稳定可靠
- 兼容现有标准，适合安全团队和自动化验证工具使用
软件供应链安全需支持动态执行环境下可复现性与漏洞评估的溯源机制。传统软件物料清单（SBOM）仅提供静态依赖清单，无法捕捉运行时行为、环境漂移或漏洞可利用性上下文。本文提出智能人工智能物料清单（AIBOM），通过自主、策略约束的推理将SBOM扩展为活跃的溯源资产。框架采用多智能体架构：（i）基准环境重建代理（MCP），（ii）运行时依赖与漂移监控代理（A2A），（iii）策略感知漏洞与漏洞可利用性（VEX）推理代理（AGNTCY）。三者结合运行时证据、依赖使用情况及环境缓解措施，依据ISO/IEC 20153:2025 CSAF v2.0语义生成结构化VEX断言。漏洞可利用性以结构化断言形式表达，而非强制动作。框架对CycloneDX和SPDX进行最小化、标准化的Schema扩展，记录执行上下文、依赖演化与代理决策溯源，保持互操作性。在异构分析工作负载上的评估表明，相比现有溯源系统，其在运行时依赖捕获、可复现性保真度和漏洞解释稳定性方面均有提升，且计算开销低。消融实验确认各智能体贡献独特能力，非确定性自动化可替代。
原文摘要 · Abstract (English)
Software supply-chain security requires provenance mechanisms that support reproducibility and vulnerability assessment under dynamic execution conditions. Conventional Software Bills of Materials (SBOMs) provide static dependency inventories but cannot capture runtime behaviour, environment drift, or exploitability context. This paper introduces agentic Artificial Intelligence Bills of Materials (AIBOMs), extending SBOMs into active provenance artefacts through autonomous, policy-constrained reasoning. We present an agentic AIBOM framework based on a multi-agent architecture comprising (i) a baseline environment reconstruction agent (MCP), (ii) a runtime dependency and drift-monitoring agent (A2A), and (iii) a policy-aware vulnerability and VEX reasoning agent (AGNTCY). These agents generate contextual exploitability assertions by combining runtime execution evidence, dependency usage, and environmental mitigations with ISO/IEC 20153:2025 Common Security Advisory Framework (CSAF) v2.0 semantics. Exploitability is expressed via structured VEX assertions rather than enforcement actions. The framework introduces minimal, standards-aligned schema extensions to CycloneDX and SPDX, capturing execution context, dependency evolution, and agent decision provenance while preserving interoperability. Evaluation across heterogeneous analytical workloads demonstrates improved runtime dependency capture, reproducibility fidelity, and stability of vulnerability interpretation compared with established provenance systems, with low computational overhead. Ablation studies confirm that each agent contributes distinct capabilities unavailable through deterministic automation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。