Related Experiment Videos
Execution-bound advisory automation for agentic AI: a reproducible AIBOM-driven CSAF-VEX framework.
Petar Radanliev1,2, Omar Santos3, Carsten Maple2,4
1Department of Computer Sciences, University of Oxford, Oxford, United Kingdom.
Frontiers in Artificial Intelligence
|June 1, 2026
Summary
This study introduces a new framework for Agentic AI supply chain security. It combines Software Bills of Materials (SBOM) and Artificial Intelligence Bills of Materials (AIBOM) with runtime telemetry for accurate exploitability assessment.
Area of Science:
- Computer Science
- Artificial Intelligence
- Cybersecurity
Background:
- Agentic AI systems present unique security challenges due to complex integrations not visible in static Software Bills of Materials (SBOMs).
- Existing security advisory workflows (CSAF/VEX) lack runtime validation, relying on static component-CVE correlation.
- Artificial Intelligence Bills of Materials (AIBOM) enhance transparency for AI-specific components but require integration with runtime data.
Purpose of the Study:
- To develop a protocol-driven framework for dynamic exploitability assessment of Agentic AI supply chains.
- To integrate static SBOM and AIBOM data with runtime telemetry for comprehensive security analysis.
- To improve the accuracy and reduce false positives in security advisories (CSAF/VEX).
Main Methods:
- A protocol-driven framework was developed, binding SBOM and AIBOM artifacts to deterministic environment capture and structured runtime telemetry.
- Exploitability was computed using declared artifacts, observed activation conditions, and enforced execution policies.
- CSAF/VEX advisories were generated from combined static and runtime evidence, validated through deterministic replay, and evaluated on synthetic Agentic AI workloads.
Main Results:
- The framework achieved a high F1-score of 0.93 (precision 0.96, recall 0.92) in exploitability assessment.
- False positives were reduced by up to 42% compared to static SBOM-CVE matching.
- Exploitability outcomes were altered in 31% of AI-specific artifact cases by incorporating AIBOM data and runtime validation.
Conclusions:
- Binding AIBOM artifacts to runtime telemetry transforms security advisory generation from static disclosure to execution-grounded exploitability assessment.
- The proposed framework enhances the security and reliability of Agentic AI supply chains.
- Deterministic replay ensures the reproducibility and trustworthiness of generated security advisories.
Related Concept Videos
01:28Automatic Processing and Automatic Social Behavior
Automatic processing refers to the cognitive operations that occur without conscious intent or awareness, playing a fundamental role in shaping social cognition and behavior. These processes enable individuals to navigate complex social environments efficiently by relying on mental shortcuts and pre-existing knowledge structures known as schemas. One of the most influential mechanisms underlying automatic processing is priming, which subtly activates mental representations through exposure to...
01:06Fixed Action Patterns
A fixed action pattern (FAP) is a specific, hard-wired sequence of behaviors that occurs in response to an external stimulus, called a sign stimulus. The behavior is “fixed” because it is essentially unchangeable—proceeding similarly across individuals of a species every time it occurs.
01:25Distribution Reliability and Automation
Distribution reliability in electrical power systems is critical for ensuring an uninterrupted power supply to consumers at minimal cost. According to IEEE Standard Terms, reliability is the probability that a device will function without failure over a specified time period or amount of usage. For electric power distribution, this translates to maintaining continuous power supply and addressing customer concerns over power outages. Several indices, as defined by IEEE Standard 1366-2012, are...
01:16Non-equilibrium in the Cell
An important concept in studying metabolism and energy is that of chemical equilibrium. Most chemical reactions are reversible. They can proceed in both directions, releasing energy into their environment in one direction, and absorbing it from the environment in the other direction. The same is true for the chemical reactions involved in cell metabolism, such as the breaking down and building up of proteins into and from individual amino acids, respectively. Reactants within a closed system...
01:16Statically Indeterminate Problem Solving
Statically indeterminate problems are those where statics alone can not determine the internal forces or reactions. Consider a structure comprising two cylindrical rods made of steel and brass. These rods are joined at point B and restrained by rigid supports at points A and C. Now, the reactions at points A and C and the deflection at point B are to be determined. This rod structure is classified as statically indeterminate as the structure has more supports than are necessary for maintaining...
01:29Impression Management Techniques III: Aligning Actions
Aligning actions are communicative strategies individuals employ to maintain social harmony and preserve personal identity in the face of potential disruptions to social norms. These actions are particularly important in managing social impressions when one's behavior might be seen as inappropriate, incompetent, or morally questionable.Types of Aligning ActionsThe three principal types of aligning actions are disclaimers, accounts, and apologies.DisclaimersDisclaimers are preventive; they are...