Examples of Features and Technical Specifications

One example of Tenable’s use of AI is the Vulnerability Priority Rating (VPR) model, which uses machine learning to predict the likelihood of a CVE being targeted for exploitation in the next 28 days. This dynamic model runs every 24 hours, taking into account the latest threat and vulnerability data for updated VPR scores. The model is trained using a Random Forest classifier that uses CVEs exploited within a 28-day period as the target variable.

Another example is the Attack Path Summary feature, which utilizes a pre-trained large language model to provide a contextual summary of specific attack paths. Users can provide feedback using a thumbs-up/thumbs-down system to improve the accuracy and effectiveness of the feature. For more information, see the relevant links below.

Further, Tenable Hexa AI is an example of applying agentic AI. When a user asks Hexa AI to “tag all my Windows Server assets and build a compliance dashboard,” Hexa AI breaks the request into a sequence of steps: search the asset inventory for Windows Server assets, identify or create the appropriate tag, request user approval to apply the tag at scale, apply the tag upon confirmation, and create a dashboard from a relevant template with the new tag applied as a context filter. Each step that changes data (applying tags, creating a dashboard) requires explicit user approval before it runs. Hexa AI operates against the same Tenable platform capabilities a user would access directly, so all actions respect the user’s existing access permissions and are fully auditable.