The U.S. Department of Energy (DOE) is developing artificial intelligence-powered tools to strengthen the cybersecurity and operational resilience of the nation’s critical infrastructure against cyberattacks through a new program examining the intersection of AI, cybersecurity and the energy sector. The Artificial Intelligence for Operationally Resilient Technologies and Systems (AI-FORTS) initiative, overseen by DOE’s Office of Cybersecurity, Energy Security, and Emergency Response (CESER), focuses on developing superintelligence-powered capabilities to help defend critical infrastructure, Sage Briscoe, CESER technical program manager and head of AI-FORTS, told GovCIO Media & Research.
AI-FORTS aligns directly with the first strategic goal outlined in CESER’s Strategic Plan Fiscal Years 2026 to 2030—Goal 1: Develop world-class security technologies. CESER partners with DOE’s National Laboratories and utilities across the country to develop AI capabilities to advance the three pillars of the AI-FORTS program.
The AI-FORTS program is built on three pillars. The first, Secure From AI, addresses a threat landscape that is evolving rapidly, with malicious actors increasingly using large language models (LLMs) and other AI tools to exploit cyber vulnerabilities, including in critical infrastructure. This pillar focuses on defending energy infrastructure against AI-enabled attacks and on developing the evaluation and stress-testing methods needed to anticipate and mitigate those threats.
The second pillar, Secure With AI, focuses on applying AI to enhance energy security. This includes developing cutting-edge tools and methods for threat detection, threat hunting, operational technology (OT) and industrial control system (ICS) visibility, anomaly detection, incident response decision support, automated assessment workflows, and operate-through-compromise resilience.
The third pillar, Secure AI, recognizes that although AI can improve the energy sector’s performance and effectiveness, the AI systems used in the sector can also become targets of attack. This pillar will support hardening of the AI used to operate, control or defend U.S. energy systems. Together, the program will reduce exposure to AI-enabled threats through systematic evaluation and countermeasures, increase AI-enabled defensive capabilities, and ensure that AI used in energy systems is trustworthy, secure and resilient.
AI-FORTS launched in 2024, with several projects getting under way in summer 2025. The program also brought ongoing DOE research, including Communications and Cybersecurity for the Energy Edge (C2E2), under one initiative, consolidating work on novel machine learning techniques, Briscoe explained. The work is beginning to bear fruit, she said, but much remains to be done, noting that the accelerating pace of development as the technology matures is one of the challenges of SI research.
DOE plans for AI-FORTS to be a long-term research effort. CESER and DOE are working with industry to tap expertise and develop solutions, and in the coming months and years, the program will continue to draw on industry resources to turn research into practical capabilities that strengthen national energy security.
“We really want to keep looking for new ways to adapt, innovate and make sure that we keep pushing the needle forward,” she said.
Back in September, the CESER and Sandia National Laboratories announced a deal on the C2E2 initiative that automates power grid data engineering and enables utility operators to detect and locate the source of cyber threats. The effort will explore how artificial intelligence (AI) can strengthen electric grid security and help operators detect, locate and respond to attacks. Part of CESER’s AI-FORTS program, C2E2 uses large language models (LLMs) and generative AI to help grid security operators quickly identify when and where system attacks take place.
