Delivered an Invited Talk at the ACM Workshop on Wireless Security and Machine Learning
July 03, 2025
Our President and CEO, Dr. Sastry Kompella delivered an invited talk titled “From Signals to Strategy: DoD Perspectives on Machine Learning in Wireless and Spectrum Security” at the ACM Workshop on Wireless Security and Machine Learning (WiseML).
In this engaging session, Dr. Kompella highlighted emerging Department of Defense (DoD) perspectives on the role of machine learning in enhancing wireless communications and securing the electromagnetic spectrum. Drawing on both operational needs and recent research, the talk explored the transition from raw signal processing to strategic decision-making enabled by AI. Specifically, he discussed three relevant topics, namely Spectrum auctions (AWS-3, AMBIT, EMBRSS), Integrated Sensing and Communications (ISAC) and Zero Trust networking.
We thank the organizers of ACM WiseML Workshop for the opportunity and look forward to continued collaboration with the defense, academic, and technology communities on this critical topic.
AI Cybersecurity research presented at the ACM Workshop on Wireless Security and Machine Learning
July 03, 2025
Recent findings on Nexcepta's Artificial Intelligence (AI) Cybersecurity research have been presented at the ACM Workshop on Wireless Security and Machine Learning (WiseML). Please see below for details.
Title: Distributed Federated Learning for Vehicular Network Security: Anomaly Detection Benefits and Multi-Domain Attack Threats
Abstract: In connected and autonomous vehicles, machine learning for safety message classification has become critical for detecting malicious or anomalous behavior. However, conventional approaches that rely on centralized data collection or purely local training face limitations due to the large scale, high mobility, and heterogeneous data distributions inherent in inter-vehicle networks. To overcome these challenges, this paper explores Distributed Federated Learning (DFL), whereby vehicles collaboratively train deep learning models by exchanging model updates among one-hop neighbors and propagating models over multiple hops. Using the Vehicular Reference Misbehavior (VeReMi) Extension Dataset, we show that DFL can significantly improve classification accuracy across all vehicles compared to learning strictly with local data. Notably, vehicles with low individual accuracy see substantial accuracy gains through DFL, illustrating the benefit of knowledge sharing across the network. We further show that local training data size and time-varying network connectivity correlate strongly with the model's overall accuracy. We investigate DFL's resilience and vulnerabilities under attacks in multiple domains, namely wireless jamming and training data poisoning attacks. Our results reveal important insights into the vulnerabilities of DFL when confronted with multi-domain attacks, underlining the need for more robust strategies to secure DFL in vehicular networks.
5G Sidelink research presented at the 2025 Conference on Information Sciences and Systems (CISS)
March 19, 2025
Recent findings on Nexcepta's 5G Sidelink research have been presented at the 59th Annual Conference on Information Sciences and Systems (CISS). Please see below for details.
Title: Relay Selection and User Equipment Admission in Resource-Efficient NextG Sidelink Communications
Abstract: 5G/6G sidelink communications addresses the challenge of connecting outer UEs, which are unable to directly access a base station (gNodeB), through inner UEs that act as relays to connect to the gNodeB. The key performance indicators include the achievable rates, the number of outer UEs that can connect to a gNodeB, and the latency experienced by outer UEs in establishing connections. We consider problem of determining the assignment of outer UEs to inner UEs based on the channel, interference, and traffic characteristics. We formulate an optimization problem to maximize a weighted sum rate of UEs, where weights can represent priority, waiting time, and queue length. This optimization accommodates constraints related to channel and interference characteristics that influence the rates at which links can successfully carry assigned traffic. While an exhaustive search can establish an upper bound on achievable rates by this non-convex optimization problem, it becomes impractical for larger number of outer UEs due to scalability issues related to high computational complexity. To address this, we present a greedy algorithm that incrementally selects links to maximize the sum rate, considering already activated links. This algorithm, although effective in achieving high sum rates, may inadvertently overlook some UEs, raising concerns about fairness. To mitigate this, we introduce a fairness-oriented algorithm that adjusts weights based on waiting time or queue length, ensuring that UEs with initially favorable conditions do not unduly disadvantage others over time. We show that this strategy not only improves the average admission ratio of UEs but also ensures a more equitable distribution of service among them, thereby providing a balanced and fair solution to sidelink communications.
Nexcepta Assessed “Awardable” for DARPA ERIS Marketplace
Press Release:
Nexcepta Assessed “Awardable” for DARPA ERIS Marketplace, Gaithersburg, MD.
June 12, 2025 – Nexcepta Inc, a leading provider of DoD R&D services today announced that it has achieved “Awardable” status through DARPA Expedited Research Implementation Series (ERIS) Marketplace. The ERIS Marketplace is a transformative digital platform designed to accelerate acquisition velocity and advance national security innovation. All 7-minute awardable solutions housed in the repository have been assessed through comprehensive scoring rubrics and competitive procedures and are readily available for selection, negotiation, and award by Government customers with a Marketplace account. Government customers can create an account at www.darpaconnect.com/eris.
Nexcepta’s solutions are designed to leverage AI/ML for next-generation protocol generation and signal optimization across wireless networks, particularly in contested and dynamic environments. They are used by a wide range of organizations, including defense agencies, national laboratories, and advanced R&D groups within the DoD ecosystem.
“Being recognized as ‘Awardable’ on the ERIS Marketplace affirms the impact of our innovative AI-driven networking solutions for national defense, especially in pushing the boundaries of how wireless protocols can be learned and adapted in real-time,” said Dr. Sastry Kompella, CEO of Nexcepta. “Our semantic protocol generation approach introduces a new paradigm in machine-learned protocol stacks that adapt to goals like low latency, resilience, and adversarial robustness, offering a disruptive leap beyond current protocol engineering,” said Dr. Yalin Sagduyu, CTO of Nexcepta. Nexcepta's solution titled “AI-based Semantic Protocol Generation,” accessible only by government customers on the DARPA ERIS Marketplace, presents an actual use case in which the company envisions an AI model that can generate novel wireless protocol behaviors using multi-modal inputs (e.g., signal characteristics, flow and traffic statistics, and context-based constraints), generate task-specific protocol functions, and operate under adversarial conditions such as jamming and delay.
Nexcepta was recognized among a competitive field of applicants to the ERIS Marketplace whose solutions demonstrated innovation and potential impact on DoD missions. Government customers interested in viewing the video solution can create an ERIS Marketplace account at www.darpaconnect.us/eris.
About Nexcepta: Nexcepta is a leading R&D firm advancing national security through pioneering research in AI/ML, wireless communications, and cybersecurity. Headquartered in Gaithersburg, MD, Nexcepta supports a wide array of DoD customers with innovative solutions that address critical challenges in spectrum operations, tactical networking, protocol generation, and autonomous system security. Through its interdisciplinary expertise and collaborative partnerships, Nexcepta delivers cutting-edge technologies that transition into operational advantage.
About the ERIS Marketplace: The DARPA Expedited Research Implementation Series (ERIS) Marketplace is a transformative digital platform designed to accelerate acquisition velocity and advance national security innovation. All 7-minute awardable solutions housed in the repository have been assessed through complex scoring rubrics and competitive procedures and are readily available for selection, negotiation, and award by Government customers with a Marketplace account. By streamlining the procurement process, the ERIS Marketplace empowers DoD organizations to rapidly acquire disruptive technologies that address the evolving challenges of defense and security. Industry and academia are encouraged to showcase their innovative solutions, connecting directly with DARPA and other government customers seeking revolutionary research and technology.
Learn more at: www.darpaconnect.com/eris.
Nexcepta Selected by the U.S. Air Force to Deliver Generative AI Technology
Jan. 29, 2025
FOR IMMEDIATE RELEASE
Nexcepta Selected by the U.S. Air Force to Deliver Generative Artificial Intelligence (GenAI) Technology
Nexcepta will develop and deploy Text-Guided Diffusion Models for Robust RF Signal Generation (DiffusionRF) technology.
(Gaithersburg, MD) – Nexcepta announces it has been selected by AFWERX for a contract focused on Text-Guided Diffusion Models for Robust RF Signal Generation (DiffusionRF) to address the most pressing challenges in the Department of the Air Force (DAF). The Air Force Research Laboratory and AFWERX have partnered to streamline the Small Business Innovation Research (SBIR) and Small Business Technology Transfer (STTR) process by accelerating the small business experience through faster proposal to award timelines, changing the pool of potential applicants by expanding opportunities to small business and eliminating bureaucratic overhead by continually implementing process improvement changes in contract execution. The DAF began offering the Open Topic SBIR/STTR program in 2018 which expanded the range of innovations the DAF funded and now on Jan. 14, 2025, Nexcepta will start its journey to create and provide innovative capabilities that will strengthen the national defense of the United States of America.
“The current state of RF signal generation predominantly relies on simulations using static signal models or limited real-world data captures. These approaches may not fully characterize the complexity of contested RF environments, are often not repeatable, and can be costly to obtain. DiffusionRF provides a cost-effective solution for generating high-fidelity electromagnetic (EM) data that is essential for training and developing advanced spectrum awareness capabilities,” says Dr. Sastry Kompella, CEO of Nexcepta. “DiffusionRF is crucial for maintaining spectrum dominance and ensuring mission success in contested environments in addition to supporting spectrum coordination and management in commercial NextG communications systems.”
“The views expressed are those of the author and do not necessarily reflect the official policy or position of the Department of the Air Force, the Department of Defense, or the U.S. government.”
About Nexcepta
Nexcepta is a leading research and development (R&D) firm delivering innovative technical solutions, mission-critical capabilities, and commercial products, along with tailored R&D and engineering services for federal and commercial clients. Nexcepta offers a comprehensive portfolio of interdisciplinary solutions spanning NextG communications and networks, cybersecurity, computing, artificial intelligence, machine learning, and data analytics.
About AFRL
The Air Force Research Laboratory is the primary scientific research and development center for the Department of the Air Force. AFRL plays an integral role in leading the discovery, development, and integration of affordable warfighting technologies for our air, space and cyberspace force. With a workforce of more than 12,500 across nine technology areas and 40 other operations across the globe, AFRL provides a diverse portfolio of science and technology ranging from fundamental to advanced research and technology development. For more information, visit afresearchlab.com.
About AFWERX
As the innovation arm of the DAF and a directorate within the Air Force Research Laboratory, AFWERX brings cutting-edge American ingenuity from small businesses and start-ups to address the most pressing challenges of the DAF. AFWERX employs approximately 370 military, civilian and contractor personnel at five hubs and sites executing an annual $1.4 billion budget. Since 2019, AFWERX has executed over 6,200 new contracts worth more than $4.7 billion to strengthen the U.S. defense industrial base and drive faster technology transition to operational capability. For more information, visit afwerx.com.
Company Press Contact:
Dr. Sastry Kompella
CEO, Nexcepta, Inc.