The Defense Information Systems Agency (DISA) is seeking industry input on artificial intelligence (AI) and machine learning (ML) models, tools, and services to improve its Defensive Cyber Operations (DCO).
In a request for information (RFI) published on sam.gov on March 25, DISA outlines its interest in exploring the potential applications of commercial AI/ML models, tools, services, and best practices to augment and enhance its current DCO capabilities and methods.
The deadline for responses to the RFI is April 30.
Specifically, the RFI highlights that DISA is keen to know how AI-based solutions “can be applied to proactively detect unknown cyber threats from cyber sensor data and real-time threat intelligence that generates actionable, prioritized leads for cyber DCO analysts.”
DISA is responsible for conducting defensive cyber operations —which consist of passive and active activities intended to preserve the ability to use DoD cyberspace capabilities and protect DoD data, networks, and systems. However, a major challenge facing DCO analysts is the huge volumes of cybersecurity data.
“As cyber threats proliferate — both in terms of numbers and sophistication — the ability of DISA to successfully perform the defensive cyber operations becomes more and more challenging. To overcome these challenges, DISA is interested in exploring the potential of applying commercial AI/ML models, tools, services, and best practices to augment and enhance its current DCO capabilities and methods,” the RFI states.
AI-powered solutions could help analyze vast amounts of log, sensor, alert, and telemetry data to identify anomalous and potentially malicious activity. AI-powered solutions can help proactively detect unknown cyber threats, generating actionable, prioritized leads for cyber DCO analysts by automating data exploration, correlation, and log analysis.
DISA is specifically seeking a complete AI/ML platform that includes a data acquisition and processing solution, a model development pipeline, and an operations and sustainment strategy.
“This AI/ML platform can be on-premises, in the cloud, or a hybrid approach,” the RFI states.
