Cici: ipaai: XAI-driven data forensics for nuclear edge llms: provenance, detection, and recovery
Active Project Grant Awarded
- Award ID
- 2641406
- Recipient
-
Lehigh University UEI E13MDBKHLDB5
- Awarding agency
-
Office of Advanced Cyberinfrastructure
National Science Foundation
- Obligated
- $899,868
Award facts
- Assistance listing
- 47.070 Computer and Information Science and Engineering
- Completion date 6% complete
- Place of performance
- Fountain Hill, PA 18015, USA
Award details come from USAspending.gov.
About this award
The National Science Foundation's Office of Advanced Cyberinfrastructure awarded Lehigh University, doing business as Office of Research, $899,868 on September 9, 2026, under the Computer and Information Science and Engineering program (CFDA 47.070). The program supports investigator-initiated research and education across computing, communications, and information science and engineering, and advances research cyberinfrastructure.
The project builds an explainable artificial intelligence framework that secures the full workflow of large language models used in nuclear-domain applications, including on-site models that support reactor operators. Interpretability methods trace model outputs to specific inputs and internal representations, then detect and remove poisoned or low-quality training data through machine unlearning. Hardware-based fingerprinting confirms model origin. At inference time, layered defenses screen inputs, flag risky prompts, and validate outputs before any recommendation reaches an operator. The methods are validated with real operational data from a research nuclear reactor. Deliverables include openly shared tools, datasets, and a fingerprint library, along with new university courses and K-12 outreach to build a security-aware technical workforce.
The period of performance runs from the September 9, 2026 award date to an ultimate completion date of October 31, 2029. Place of performance is Fountain Hill, Pennsylvania 18015, USA. The source names no sub-recipients for this award.
Description
- Abstract
- Nuclear reactors supply a large share of reliable electricity, and reactor operators increasingly turn to large language models to help interpret procedures, sensor logs, and alarm messages in real time. Running these models on-site, close to the reactor, keeps sensitive data in-house and speeds decision-making, but IT also opens new ways for these systems to fail or be attacked. Poisoned or low-quality training data, foundation models that carry hidden backdoors, and manipulated prompts can each push a model toward confident but incorrect recommendations, a serious hazard that could threaten safety or force a costly shutdown. This project builds an explainable artificial intelligence framework that secures the entire workflow of nuclear-domain large language models. The team develops interpretability methods that trace a model's outputs back to specific inputs and internal representations, then uses those signals to detect and remove poisoned or low-quality training data through machine unlearning. To confirm a model's origin, hardware-based fingerprinting techniques are employed. At inference time, layered defenses screen inputs, flag risky prompts, and validate outputs before any recommendation reaches an operator. The methods are validated with real operational data from a research nuclear reactor. By establishing a unified approach to data integrity, model provenance, and output reliability, the project advances the safe deployment of large language models in critical infrastructure, protecting public welfare and national security. Openly shared tools, datasets, and a fingerprint library, along with new university courses and K?12 outreach, will help build a security-aware technical workforce. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the foundation's intellectual merit and broader impacts review criteria.- subawards are not planned for this award.
Quick answers
Who received award 2641406?
2641406 was awarded to Lehigh University by Office of Advanced Cyberinfrastructure (National Science Foundation) on September 9, 2026.
How much is award 2641406 worth?
$899,868 has been obligated on 2641406.
On GovTribe
See this award's full record
- Every transaction and subaward
- The recipient's other awards and teaming partners
- Similar grant awards
- Ask GovTribe AI about this award