Woburn, MA – January 27, 2025 – Rapid advancements in artificial intelligence (AI) have resulted in increased development of autonomous agents that perform complex tasks previously requiring human operators. In the academic domain, AI agents have been used to defeat world-class experts in games such as Go and Shogi, and more recently, multiplayer games such as Quake III, Starcraft II and DOTA II. The DoD has rapidly adapted these technologies for a variety of tasks including mission planning, air combat operations, and missile defense. As with any rapidly advancing technology, identifying the weakness and vulnerabilities of the technology are as important as advancing the technology itself, which exploit the fragility of AI models often underpinning these autonomy solutions. However, these efforts typically focus only on perturbation in input data received by an AI model and not the autonomy system as a whole.

PHILIPPINE SEA (March 14, 2023) – An Aerosonde unmanned aerial system (UAS) assigned to the Arleigh Burke-class guided-missile destroyer USS Milius (DDG 69) launches from the ship’s flight deck while operating in the Philippine Sea, March 14. Milius is assigned to Commander, Task Force 71/Destroyer Squadron (DESRON) 15, the Navy’s largest forward-deployed DESRON and the U.S. 7th Fleet’s principal surface force. (U.S. Navy photo by Mass Communication Specialist 1st Class Greg Johnson)

Aptima, Inc. and partner PatchPlus Consulting are addressing the Navy’s problem of defending current and future autonomous aerial systems against counter-counter measures by building a large language model (LLM)-driven development agent named STAR (System for Threat Analysis and Response) that will function to not only generate a taxonomy of the attack surface, but also form a full, future-adapting test suite for AI developers through specialized agents. The first agent, the Security Knowledge Generator (SKG), will construct and continually update a structured, annotated knowledge representation of the attacks, defenses, example vignettes, systems, and functions for Naval Intelligent Autonomous Systems (IAS). The second agent, the Scenario and Code Generator (SCG), will create the security scenarios for a given autonomy system. The scenarios will include the step-by-step instructions for attacking or defending the autonomous system and AI-based functional modules of interest that will include text descriptions for high-level system components and the code templates for the steps that correspond to individual AI modules. Finally, the third agent, the Evaluation Report Generator (ERG), will parse the results of the experiments and user-system analysis to construct the aggregated, user-readable evaluation report cards describing the IAS assessment process and summary of results.

STAR is a part of Aptima’s Trustworthy ArtificiaI Intelligence (AIT) portfolio of technologies. AIT aims to enhance transparency, evaluation, validation, and compliance within AI systems to foster human-machine collaboration and continuous improvement in mission critical environments.

Stay in touch! Sign up for our newsletter, The Aptimist

Discover how Aptima is shaping the future of defense, intelligence, and healthcare through inspiring stories, expert insights, and more by subscribing to our monthly newsletter. Visit The Aptimist to subscribe today!