Cyber Collaborative Research Alliance
This project fosters cyber research, performed by a competitively selected consortium, formed to advance the theoretical foundations of cyber science in the context of Army networks. This work consists of academia, industry, and government researchers working jointly to develop a fundamental understanding of cyber phenomena so that fundamental laws, theories, and theoretically grounded and empirically validated models can be applied to a broad range of Army domains, applications, and environments. This research focuses on three interrelated cyber aspects and is conducted using a trans-disciplinary approach that takes into account the human element of the network. The three aspects of cyber that are addressed are: 1) adaptive reasoning for deception, 2) anticipating, detecting, and analyzing malicious activities, and 3) agile cyber maneuver to thwart and defeat malicious activities. The overarching goals are to significantly decrease the adversary's return on investment when considering cyber-attack on Army networks and minimizing the impact on Army network performance. This research creates a framework that effectively integrates the knowledge of cyber assets and potential adversary capabilities and approaches and provides defense mechanisms that dynamically adjust to changes related to mission, assets, vulnerability state, and defense mechanisms. Work in this project is performed by the Army Research Laboratory (ARL).
FY2026 to FY2027 change Funding decrease reflects transfer to Program Element (PE) 0601104A (Army Collaborative Research and Tech Alliances) / Project AB7 (Army Collaborative Research and Tech Alliances) to streamline and optimize the Science and Technology (S&T) portfolio and align all non-Electronic Warfare CRAs under one project.
FY2026 plans — current year Will investigate the theoretical foundation of multidomain deception in complex systems and adversarial environments for tactical applications; develop measures of trustworthiness and robustness for complex systems; research innovative machine learning techniques which minimize the need for continual retraining and are resilient against adversarial attacks; investigate innovative approaches to support classifier training in simulated environments that will effectively and efficiently transfer to the deployed environment with minimal labeled data from captured network packets in the target environment.
FY2025 accomplishments Will conduct research into methodologies to identify, predict, reason, create, and exploit cyber security Windows of Superiority; explore techniques to enable multidomain cyber deception in contested environments; explore techniques to counter adversarial attacks and manipulation of machine learning based algorithms utilized for network defenses; examine impact of uncertainties and incomplete information in machine learning algorithms for cyber deception and network intrusion detection.