CTC Develops Machine Learning Tool to Protect Against Adversarial Attacks and Privacy Vulnerabilities in Defense Applications
NATO AI Security Symposium Best Paper Award
Johnstown, PA, Sept. 10, 2026 (GLOBE NEWSWIRE) — Concurrent Technologies Corporation (CTC) is working as a partner on a cutting-edge research project with the Robotics Research Center (RRC) at the United States Military Academy, West Point.
The project focuses on designing and engineering a machine learning (ML) model-stealing pipeline as part of an AI Security Assessment Tool for automated developmental test and evaluation tools and metrics. CTC is also conducting novel scientific research with the RRC using this innovative pipeline.
The ML model-stealing pipeline addresses critical security vulnerabilities in artificial intelligence systems. Use cases for this technology include identifying which ML model architectures and training techniques are more susceptible to privacy leaks and developing and testing defenses such as differential privacy or adversarial training to protect against various stealing attacks.
Additional applications include evaluating privacy-preserving techniques that make it harder for attackers to infer hidden characteristics of training datasets, revealing which architectures are inherently more resistant to different attack types, and identifying specific model components or features most vulnerable to exploitation.
“This partnership with West Point’s Robotics Research Center represents a significant step forward in securing AI systems against emerging threats,” said Dave Saranchak, CTC Executive Director. “Our team is proud to contribute our expertise in developing tools that will help protect critical machine learning models from adversarial attacks and unauthorized access. This work is essential to maintaining the integrity and security of AI systems that our nation depends on.”
CTC is leveraging multiple proprietary codebases previously developed for similar tasks, combining them within this comprehensive pipeline. The components are designed to be modular and reconfigurable to support a wide range of experimental designs, providing flexibility and scalability for future research applications.
“As artificial intelligence becomes increasingly integrated into defense and national security applications, ensuring the security and integrity of these systems is paramount,” said Chris Hamilton, CTC President and CEO. “We are deeply honored to work alongside the talented researchers at West Point’s Robotics Research Center. This project exemplifies CTC’s commitment to advancing the state of the art in AI security while supporting our nation’s military readiness and technological superiority.”
The collaboration with the U.S. Military Academy underscores CTC’s ongoing dedication to supporting Department of War research priorities and developing innovative solutions to complex technical challenges.
Concurrent Technologies Corporation (CTC) is an independent, nonprofit, applied scientific research and development professional services organization. CTC collaborates with its technology transition affiliate, Enterprise Ventures Corporation, to provide transformative, full lifecycle solutions through research, development, test, and evaluation work. To best serve its clients’ needs, CTC offers the complete ability to fully design, develop, test, prototype, and build. CTC delivers robust, technical, and innovative solutions that safeguard our national security, retain U.S. technological advantage, and ensure the primacy of American manufacturing. For more information, visit www.ctc.com.
PHOTO CAPTION:
Dave Saranchak, CTC Executive Director, received the Best Paper Award at the NATO AI Security Symposium. The paper highlighted CTC research on ML model security, which supports CTC’s collaboration with West Point’s Robotics Research Center. Pictured are paper contributors (L to R) Jessica Carpenter, Tyler Shumaker, Dave Saranchak, and COL Nathaniel Bastian
Attachment
- NATO AI Security Symposium Best Paper Award
CONTACT: Mary Bevan Concurrent Technologies Corporation 814-269-2490 [email protected]
