N231-067 TITLE: Cognitive Tactics, Techniques and Procedures (TTP) Synthesis

OUSD (R&E) CRITICAL TECHNOLOGY AREA(S): Artificial Intelligence (AI)/Machine Learning (ML); Autonomy

The technology within this topic is restricted under the International Traffic in Arms Regulation (ITAR), 22 CFR Parts 120-130, which controls the export and import of defense-related material and services, including export of sensitive technical data, or the Export Administration Regulation (EAR), 15 CFR Parts 730-774, which controls dual use items. Offerors must disclose any proposed use of foreign nationals (FNs), their country(ies) of origin, the type of visa or work permit possessed, and the statement of work (SOW) tasks intended for accomplishment by the FN(s) in accordance with the Announcement. Offerors are advised foreign nationals proposed to perform on this topic may be restricted due to the technical data under US Export Control Laws.

OBJECTIVE: Synthesize Artificial Intelligent (AI)-generated Electronic Support (ES) and Electronic Attack (EA) Tactics, Techniques and Procedures (TTPs) in near real-time against known legacy or unknown/complex sensor waveforms using online and unsupervised Machine Learning Algorithms (MLAs) based on real-time collaborative Tactical Situational Awareness and mission objectives for Size, Weight, and Power (SWaP)-constrained unmanned and/or manned naval platforms.

DESCRIPTION: Research will develop AI-generated, machine actionable ES and EA TTPs in near real-time using online and unsupervised MLAs based on all-available information and multi-modality data present in the Electromagnetic (EM) Spectrum for a single platform & across multiple collaborative Manned/Unmanned naval platforms. Capabilities being developed include:

� Self and collaborative real-time tactical situational assessment and predicted TTP needs against current and anticipated (near and far-term) adversary Intelligence, Surveillance, Reconnaissance and Targeting (ISRT) systems and associated kill chains to achieve mission objectives using game theoretic algorithms and machine learning enhanced micro-simulations.

� Multi-dimensional stochastic analysis for rapid AI-decision making for supporting near-term tactical objectives and long-term strategic goals.

� Autonomously-generated and machine deployable TTP source-code, testing and implementation that is reacting within an adversary�s sensor Coherent Processing Interval (CPI), and continues adapting and refining the newly formed TTP based on subsequent observations.

� Automated deployment of AI-derived and tested TTPs between collaborative platforms to support current and future engagements that permits continued adaptation and refinement of the TTP from a collaboration perspective.

 

This approach extends beyond traditional library look-up solutions that are typically pre-loaded in an on-board Mission Data File (MDF). This research and development activity is envisioned to initially augment , and eventually replace, traditional Electronic Support Measures (ESM) techniques libraries/databases while reducing offline human-derived TTP development, analysis, and testing timeline by orders of magnitude.

Work produced in Phase II may become classified. Note: The prospective contractor(s) must be U.S. Owned and Operated with no Foreign Influence as defined by DOD 5220.22-M, National Industrial Security Program Operating Manual, unless acceptable mitigating procedures can and have been implemented and approved by the Defense Counterintelligence Security Agency (DCSA), formerly the Defense Security Service (DSS). The selected contractor must be able to acquire and maintain a secret level facility and Personnel Security Clearances, to perform on advanced phases of this contract as set forth by DCSA and ONR to gain access to classified information pertaining to the national defense of the United States and its allies; this will be an inherent requirement. The selected company will be required to safeguard classified material IAW DoD 5220.22-M during the advance phases of this contract.

PHASE I: Define, develop, and deliver algorithm designs, architectures, flow diagrams, and processes that clearly articulates how the program�s objectives and capabilities will be achieved and implemented into research-level or prototype code during Phase II activities.

PHASE II: Develop, document, demonstrate, and deliver research-level or prototype code, libraries, executables, and necessary software artifacts that successfully achieves the program�s objectives and capabilities as defined in Phase I. A Subsequent Phase II award would further mature, demonstrate, validate, and deliver research-level or prototype code, libraries, executables, and necessary software artifacts to support accelerated transition to the Program-of-Record.

It is probable that the work under this effort will be classified under Phase II (see Description section for details).

PHASE III DUAL USE APPLICATIONS: Integrate the Phase II developed software with an on-board flight computer and Electronic Warfare systems, flight test the completed prototype system in a tactically-relevant environment, and integrate into a future FNC program for transition to a naval unmanned, and/or manned airborne platform.

Work products and deliverables are expected to be classified.

REFERENCES:

1.       Pehlevan, C. and Chklovskii, D. "Neuroscience-Inspired Online Unsupervised Learning Algorithms: Artificial Neural Networks." IEEE Signal Processing Magazine, Vol 36, Issue 6, Nov-2019.

2.       Loaiza, F.; Wheeler, D. and Birdwell, J. "A Partial Survey on AI Technologies Applicable to Automated Source Code Generation." Institute for Defense Analyses (IDA), IDA NS D-10790, Sep-2019.

3.       Le, T,H.M.; Chen, H. and Ali Babar, M. "Deep Learning for Source Code Modeling & Generation: Models, Applications and Challenges." ACM Computing Surveys, Vol 53, Issue 2, May-2021.

4.       Rajeswaran, A.; Mordatch, I. and Kumar, V. "A Game Theoretic Framework for Model Based Reinforcement Learning." Proceedings of the 37th International Conference on Machine Learning, PMLR Vol 119, 2020.

5.       Albrecht, C.; Marianno, F. and Klein, L. "AutoGeoLabel: Automated Label Generation for Geospatial Machine Learning." 2021 IEEE International Conference on Big Data, 2021.

 

KEYWORDS: Autonomous Tactical TTP Generation; Tactics, Techniques and Procedures; Online, Unsupervised Machine Learning; Automated Model Generation; Compressed Model Representation; Real-Time Analytics; SWaP-Constrained Platform Processing; Data Compression; Automa

---