In progress – view active session
Conference 13058
Disruptive Technologies in Information Sciences VIII
22 - 24 April 2024 | National Harbor 6
View Session 
Session 1:
AI Methodologies and Applications I
22 April 2024 • 8:30 AM - 10:10 AM EDT | National Harbor 6
Session Chair:
Nelson Jaimes, The George Washington Univ. (United States)
13058-1
22 April 2024 • 8:30 AM - 8:50 AM EDT | National Harbor 6
Show Abstract +
We report work in progress bridging the AI gap between bottom-up data-driven ML and top-down conceptually-driven symbolic reasoning. We seek explainable hybrid symbolic/numeric causal models, for prediction, what-if analysis and control, using Mutual Information, Granger causality, and Pearl causality. Next we apply these in Genetic Programming (GP) to filter the population of discovered statistical dependencies to plausibly causal relationships, represented symbolically for use by a reasoning engine in a cognitive architecture. Success could bring broader generalization, using not just learned patterns but learned general principles, enabling trustworthy AI/ML based systems to autonomously navigate complex unknown environments and handle “black swans”.
13058-2
22 April 2024 • 8:50 AM - 9:10 AM EDT | National Harbor 6
Show Abstract +
ML practice promotes self-supervised pre-training for generalized feature extraction on a diverse unlabeled dataset followed by supervised transfer learning on a smaller set of labeled, application-specific images. This shift in learning methods elicits conversation about the importance of pre-training data composition for optimizing downstream performance.
We evaluate models with varying measures of similarity between pre-training and transfer learning data compositions. Our findings indicate that front-end embeddings sufficiently generalize learned image features independent of data composition, leaving transfer learning to inject the majority of application-specific understanding into the model. Composition may be irrelevant in self-supervised pre-training, suggesting target data is a primary driver of application specificity. Thus, pre-training deep learning models with application-specific data, which is often difficult to acquire, is not necessary for reaching competitive downstream performance. The capability to pre-train on more accessible datasets invites more flexibility in practical deep learning.
13058-3
22 April 2024 • 9:10 AM - 9:30 AM EDT | National Harbor 6
Show Abstract +
Consider a sequential goal completion task, e.g. 1) pick up a key then 2) unlock the door then 3) lift the box. A monolithic artificial neural network (ANN) would have to be significantly retrained if the goals or sequence of goals change. This work instead describes a modular, hierarchical machine learning (ML) framework integrating two emerging ML techniques: 1) hyperdimensional computing (HDC) and 2) cognitive map learners (CML). HDC, as an ML symbolic algebra, was used to learn sub-goal specific scene-action behavioral policies. The CML in turn learned to optimally traverse abstract graphs, e.g. finite state machines (FSM). Critically, by describing the sequential goal completion task as an FSM, changes to goals or sequence of goals were locally constrained in the CML-HDC architecture. This framework enables a more traditional engineering approach to ML, akin to digital logic design.
13058-4
22 April 2024 • 9:30 AM - 9:50 AM EDT | National Harbor 6
Show Abstract +
We present a novel approach for designing a unilateral lower extremity exoskeleton controlled by deep reinforcement learning algorithms. The exoskeleton aims to assist in rehabilitation and improve the quality of life for individuals with lower limb disabilities. A key innovation is the integration of sensor fusion, combining surface electromyography (sEMG) and inertial measurement units (IMU) from specialized Myo-Ware bands. The collected data are fed into an LSTM-based Proximal Policy Optimization (PPO) model for real-time, adaptive control of electric motors at the knee and ankle joints. Preliminary results demonstrate the system's efficacy in a range of motion tasks that mimic aspects of the Activities of Daily Living (ADL) that a user might encounter, paving the way later for more comprehensive clinical studies that would include having paired exoskeletons for each lower extremity.
13058-5
22 April 2024 • 9:50 AM - 10:10 AM EDT | National Harbor 6
Show Abstract +
This paper presents a pioneering first-generation dive-mask integrated eye tracking system for underwater health and cognition monitoring. Building on this foundation, we're exploring its potential for enhancing human-machine teaming in low-visibility, low-communication scenarios. By harnessing eye metrics to inform decision field theory, our aim is to revolutionize task allocation in extreme environments, prioritizing safety and efficiency.
Break
Coffee Break 10:10 AM - 10:40 AM
Session 2:
AI Methodologies and Applications II
22 April 2024 • 10:40 AM - 12:00 PM EDT | National Harbor 6
Session Chair:
Nelson Jaimes, The George Washington Univ. (United States)
13058-6
22 April 2024 • 10:40 AM - 11:00 AM EDT | National Harbor 6
Show Abstract +
We have developed custom optimization techniques using quantization to accelerate 3D object detection using multi-modal sensors in tactical edge robotic systems. 3D object detection is highly useful in robotic navigation, and mission planning. Our optimization aims to improve the computation pipeline. Our method uses segmentation on the RGB channels and maps those results to the LIDAR point cloud using matrix calculations to reduce the noise. Our optimizations include quantization for the segmentation inference as well as matrix optimizations. The optimizations achieve a 3-times speed-up over the baseline algorithm which allowed us to deploy the algorithm in the field robots.
We will present our results, compare them with the baseline, and discuss their significance in achieving real-time object detection in resource-constrained tactical environments.
13058-8
22 April 2024 • 11:00 AM - 11:20 AM EDT | National Harbor 6
Show Abstract +
The advancement of open architecture ecosystems is fundamentally dependent on the interoperability, scalability, and adaptability of their constituent elements. As machine learning (ML) systems become increasingly integral to these ecosystems, the need for a systematic approach to engineer, deploy, and re-engineer them grows. This paper presents a novel modeling approach based on recently published, formal, systems-theoretic models of learning systems. These models serve dual purposes: first, they give a theoretical grounding to standards that govern the architecture, functionality, and performance criteria for ML systems; second, they allow for requirements to be specified at various levels of abstraction to ensure the systems are intrinsically aligned with the overall objectives of the open architecture ecosystem they belong to. Through the proposed modeling approach, we demonstrate how the adoption of standardized models can significantly enhance interoperability between disparate machine learning systems and other architectural components.
Show Abstract +
Large Language Models (LLMs) provide new capabilities to rapidly reform; regroup; and reskill for new missions, opportunities, and respond to an ever-changing operational landscape. Agile contracts can enable larger flow of value in new development contexts. These methods of engagement and partnership enable the establishment of high performing teams through the forming, storming, norming, and performing stages that then inform the best liberating structures that exceed traditional rigid hierarchical models or even established mission engineering methods. Use of Generative AI based on LLMs coupled with modern agile model-based engineering in design allows for automated requirements decomposition trained in the lingua franca of the development team and translation to the dialects of other domain disciplines with the business acumen afforded by proven approaches in industry. Cutting-edge AI automations to track and adapt knowledge, skills, and abilities across ever changing jobs and roles will be illustrated using prevailing architecture frameworks, model based system engineering, simulation, and decision making assisted approaches to emergent objectives.
13058-50
22 April 2024 • 11:40 AM - 12:00 PM EDT | National Harbor 6
Show Abstract +
Space 2.0 evolution is moving at an incredible pace. New entrants with new capabilities, and existing businesses are either skyrocket, pivot, or fold making long term forecasts of little use beyond the current year. To keep one’s finger on this pace of business, annual updates of what is evolving in this sector is critical for the Defense and Sensors sectors to remain aware of the threat and opportunities these developments present. Building upon last year’s well received SPIE 2023 presentation “Space 2.0: Megaconstellations”, the “Space 2.0: A Revisit” presentation is an update more focused on the needs conference attendees. Focus areas will be on updating last year’s reporting, discussing near term thrust areas of interest, and emerging technologies and platforms forecast by developers to enter testing in 2024-2030.
Break
Lunch Break 12:00 PM - 1:00 PM
Session 3:
AI for Detection and Recognition
22 April 2024 • 1:00 PM - 2:00 PM EDT | National Harbor 6
Session Chair:
Nathan R. McDonald, Air Force Research Lab. (United States)
13058-9
22 April 2024 • 1:00 PM - 1:20 PM EDT | National Harbor 6
Show Abstract +
Large language models (LLMs), such as ChatGPT and Bard, have resulted in impressive advances within the broader Artificial Intelligence (AI) community. Despite this progress, LLMs can sometimes make knowledge up or 'hallucinate' to answer a question posed to them. Such hallucinations are problematic for high-stakes operations, and where one needs to have deep trust in the model. To better understand this problem, we search the general and scholarly web for documented instances of hallucinations and replicate them on prominent LLMs. We also categorize them in an understandable taxonomy called HALO to serve as warning signs for future generations of LLMs.
13058-10
22 April 2024 • 1:20 PM - 1:40 PM EDT | National Harbor 6
Show Abstract +
We optimized and deployed the adaptive framework Virtuoso that can maintain real-time object detection even when experiencing high contention scenarios. The original Virtuoso framework uses an adaptive algorithm for the detection frame followed by a low cost algorithm for the tracker frame which uses down-sampled images to reduce computation. One of our optimizations include detaching the single synchronous thread for detection and tracking into two parallel threads. This multi-threaded implementation allows for computationally high cost detection algorithms to be used while still maintaining real-time output from the tracker thread. Another optimization we developed uses multiple down-sampled images to initialize each tracker based on the size of the input box; the multiple down-sampled images allow each tracker to choose the optimal image size for the box that it is tracking rather than a single down-sampled image being used for all trackers.
13058-11
22 April 2024 • 1:40 PM - 2:00 PM EDT | National Harbor 6
Show Abstract +
The idea of subspace learning combined with soft partitioning and successive subspace learning has been found to yield higher accuracy for image classification on benchmark image datasets. We will present the new results and discuss its wider significance.
Session 4:
AI Systems and Decision Making I
22 April 2024 • 2:00 PM - 3:20 PM EDT | National Harbor 6
Session Chair:
Gennady Staskevich, Clarkson Univ. (United States)
13058-12
22 April 2024 • 2:00 PM - 2:20 PM EDT | National Harbor 6
Show Abstract +
In previous work we have introduced our (proposed) architecture that connects a ‘Real’ and ‘Imaginary’ Neural Network. The ‘Real’ portion is represented by exploiting Striatal Beat Frequencies in an EEG with the patented Single-Period Single-Frequency (SPSF) method and the ‘Imaginary’ is represented by a convolutional neural network transformed into bi-directional associative memory matrices. We demonstrated that we could interconnect, i.e., bridge, the intermediate layers of two broken CNNs both of which were trained for object detection and still make a good prediction. In this work we will use a dual sensory CNN implementation of speech and object detection and we will incorporate Neural Decoding into the EEG SPSF method to emulate how to circumvent the broken neural networks in a Human-Computer Interface situation.
13058-17
CANCELED: Large language models and new paths to digital transformation of the engineering enterprise
22 April 2024 • 2:20 PM - 2:40 PM EDT | National Harbor 6
Show Abstract +
This paper explores the transformative potential of Large Language Models (LLMs) in modernizing the systems and test engineering enterprise. We argue that LLMs can serve as an abstraction layer, bridging traditional engineering practices with model-based engineering without necessitating a wholesale overhaul of existing systems and workforce knowledge. By facilitating interaction with complex models, LLMs limit the need for expertise in models to leverage model-based engineering, thereby addressing a key bottleneck in the digital transformation. This paper aims to spark a strategic dialogue on the benefits, challenges, and ethical implications of deploying LLMs to modernize the engineering enterprise.
13058-14
22 April 2024 • 2:40 PM - 3:00 PM EDT | National Harbor 6
Show Abstract +
Large Language Models (LLMs) and Generative AI (GenAI) are reshaping intelligent applications. To offer rapid insights and responses in real-time applications such as autonomous vehicles, there is a shift from centralized AI to decentralized edge AI. This paper proposes a latency-aware approach to seamlessly placing GenAI services on edge cloudlets.
13058-15
22 April 2024 • 3:00 PM - 3:20 PM EDT | National Harbor 6
Show Abstract +
While AI and LLM have revolutionized natural language processing in commercial applications, significant concerns must be addressed before the technology is fully deployed within the DoD. This paper will explore the current biases in training data, ethical violations, security breaches, potential misuse, and challenges with AI and LLM interpretability. Industry, academic and government partnerships need to ensure a responsible and equitable deployment of LLMs that harnesses the full potential of the capabilities in a manner that is responsible, secure, and well understood by the end user community.
Break
Coffee Break 3:20 PM - 3:40 PM
Session 5:
AI Systems and Decision Making II
22 April 2024 • 3:40 PM - 4:20 PM EDT | National Harbor 6
Session Chair:
Gennady Staskevich, Clarkson Univ. (United States)
13058-16
22 April 2024 • 3:40 PM - 4:00 PM EDT | National Harbor 6
Show Abstract +
Decision Advantage is a goal in current and future military
operations. Achieving such an advantage can be done by degrading
adversaries' decision making ability by imposing complexity on the
decision problems they have to make. This paper describes
mathematical techniques for quantifying decision complexity in
Integrated Air Defense Systems (IADS). The methods are based on graph
properties derived from the defender's IADS' System of Systems
description and the attacker's Course of Action plan. Multiple plans
can be compared quantitatively with respect to the decision complexity
they impose on the defender.
13058-13
22 April 2024 • 4:00 PM - 4:20 PM EDT | National Harbor 6
Show Abstract +
AI-enabled capabilities are reaching the requisite level of maturity to be deployed in the real world, yet do not always make correct or safe decisions. One way of addressing these concerns is to leverage AI control systems alongside and in support of human decisions, relying on the AI control system in safe situations while calling on a human co-decider for critical situations. We extend a methodology for adversarial explanations to state-of-the-art reinforcement learning frameworks, and show how this both makes an effective decision support tool and can potentially be used in a training / learning framework to continuously improve the AI control system’s accuracy and robustness. This is paired with prior work on statistically verified criticality to indicate when AI decisions would most benefit from human oversight.
Session 6:
Metaverse, Digital, and Synthetic Technologies
22 April 2024 • 4:20 PM - 4:40 PM EDT | National Harbor 6
Session Chair:
Angela Morales
13058-7
22 April 2024 • 4:20 PM - 4:40 PM EDT | National Harbor 6
Show Abstract +
The Metaverse, an expanding virtual realm, offers innovative solutions for global issues, particularly sustainable forest management's role in combatting climate change and achieving net-zero GHG emissions. This study blends the Metaverse and serious gaming to enhance environmental awareness and informed decision-making. Immersive gaming bridges the real and virtual worlds, translating forest management data into lifelike Metaverse representations, providing advanced insights into forest ecosystems and carbon sequestration. Users can explore these virtual forests through various technologies. Leveraging real-time gaming engines, this research models Northeastern hardwood forests under different land management scenarios, focusing on visual fidelity through terrain texturing, photogrammetry-based tree modeling, and advanced foliage shaders. This innovative approach addresses knowledge gaps in forestry and climate change, aiding forest decision-makers and promoting sustainable practices. It demonstrates serious gaming's potential in sustainable forest management amid global climate challenges.
Symposium Plenary
22 April 2024 • 5:00 PM - 6:30 PM EDT | Potomac A
Session Chairs:
Tien Pham, The MITRE Corp. (United States), Douglas R. Droege, L3Harris Technologies, Inc. (United States)
View Full Details: spie.org/dcs/symposium-plenary
Chair welcome and introduction
22 April 2024 • 5:00 PM - 5:05 PM EDT
DoD's microelectronics for the defense and commercial sensing ecosystem (Plenary Presentation)
Presenter(s): Dev Shenoy, Principal Director for Microelectronics, Office of the Under Secretary of Defense for Research and Engineering (United States)
22 April 2024 • 5:05 PM - 5:45 PM EDT
NATO DIANA: a case study for reimagining defence innovation (Plenary Presentation)
Presenter(s): Deeph Chana, Managing Director, NATO Defence Innovation Accelerator for the North Atlantic (DIANA) (United Kingdom)
22 April 2024 • 5:50 PM - 6:30 PM EDT
Symposium Panel on Microelectronics Commercial Crossover
23 April 2024 • 8:30 AM - 10:00 AM EDT | Potomac A
View Full Details: spie.org/dcs/symposium-panel
The CHIPS Act Microelectronics Commons network is accelerating the pace of microelectronics technology development in the U.S. This panel discussion will explore opportunities for crossover from commercial technology into DoD systems and applications, discussing what emerging commercial microelectronics technologies could be most impactful on photonics and sensors and how the DoD might best leverage commercial innovations in microelectronics.
Moderator:
John Pellegrino, Electro-Optical Systems Lab., Georgia Tech Research Institute (retired) (United States)
Panelists:
Shamik Das, The MITRE Corporation (United States)
Erin Gawron-Hyla, OUSD (R&E) (United States)
Carl McCants, Defense Advanced Research Projects Agency (United States)
Kyle Squires, Ira A. Fulton Schools of Engineering, Arizona State Univ. (United States)
Anil Rao, Intel Corporation (United States)
Break
Coffee Break 10:00 AM - 10:30 AM
Session 9:
Data Analytics and Federated Systems
23 April 2024 • 10:30 AM - 12:10 PM EDT | National Harbor 6
Session Chair:
Jeff Anderson, Integration Innovation, Inc. (United States)
13058-27
23 April 2024 • 10:30 AM - 10:50 AM EDT | National Harbor 6
Show Abstract +
Graph Neural Networks (GNN) were originally developed to infer relationships between objects in complex graph environments such as social networks. However, they have recently been applied to other domains which naturally support graph expression, such as hardware and software analysis. We propose to extend the application of GNNs to datasets which contain a temporal component, thus enabling GNN inference of event-driven situations involving the RF spectrum. Post-battle analysis can train a GNN to identify individual subgraphs representing sequences of events. Trained GNNs can then be used in war time to infer a larger situation as a series of subgraphs are identified.
13058-28
23 April 2024 • 10:50 AM - 11:10 AM EDT | National Harbor 6
Show Abstract +
Live Training Transformations (LT2) is a diverse family of training products developed under a singular baseline controlled by the Army Program Manager Training Devices (PM TRADE). The LT2 strategy facilitates an open community accessible development environment based on open architectures and open standards where contractors add capabilities to a shared government owned development baseline. LT2 presents a unique use case for open development for families of systems, where each product is individually deployed from a common baseline with its own variations in capabilities, controls, and independently managed ATOs.
PM TRADE seeks to adopt the best practices and lesson learned from other DoD software factories to improve software quality and speed to market. Readers will learn what it takes to evolve an open development environment into an open Software Factory including adaptations for metrics, governance, and open architecture principals that enable sharing and collaboration.
13058-30
23 April 2024 • 11:10 AM - 11:30 AM EDT | National Harbor 6
Show Abstract +
The Aberdeen Architecture tracks and monitors information flows during instruction execution. Saltzer and Schroeder’s security principles define complete mediation as to verify all access rights and authority. The Aberdeen Architecture achieves near mediation complete for instruction execution. The Aberdeen Architecture uses hardware state machine monitors (hardware-based nano-OS kernels) and a tagged architecture for the trusted computing base. The state machine monitors completely virtualize the execution pipeline. The state machines monitors manage and track information flows during instruction execution. The Aberdeen Architecture tracks and monitors four information flows: instruction execution flow, control flow integrity, data flow integrity, and memory access flow integrity. This paper will focus on information flow tracking and monitoring.
Keywords: Computer architecture, tagged computer architecture, information flows, execution pipeline
13058-31
23 April 2024 • 11:30 AM - 11:50 AM EDT | National Harbor 6
Show Abstract +
In this paper, we systematically investigate the use of delays to optimize the throughput for the working Maximum-On-Ground (MOG) problem space. The MOG optimization refers to the management of the transport aircraft in-and-around an airfield. The working MOG refers to the fulfilling of the servicing requirements of the aircraft. The effective and efficient daily MOG management enables the U.S. Air Force (USAF) Air Mobility Command (AMC) to rapidly deploy and sustain the equipment, and personnel anywhere in the world. However, the seemingly solved problem can quickly grow out of hand when the number of interruptions exceed past a certain point; this due to the combinatorial nature of the scheduling problem, where the order, and the mission dependencies matter. The opportunistic delays optimization explores the trade-off space between the efficiency (throughput maximization) and the resilience to schedule disruptions.
13058-48
23 April 2024 • 11:50 AM - 12:10 PM EDT | National Harbor 6
Show Abstract +
"Deep HoriXons" is an innovative 3D virtual AI and Cybersecurity campus that leverages Generative AI, specifically ChatGPT, to enhance learning in Deep Learning AI and Cybersecurity. This platform enables students to participate as avatars in a collaborative 3D virtual environment using open-source technology.
Students engage in Deep Learning AI projects that facilitate hands-on learning and experimentation inworld. Simultaneously, "Deep HoriXons" offers classes inworld on Cybersecurity, equipping veterans, active service members, DoD government civilians, and government contractors with the knowledge needed to pass the CompTIA Security+ exam on their first attempt, even with no prior IT or cybersecurity experience.
By integrating ChatGPT, students can interact with AI for explanations, insights, and problem-solving, accelerating their comprehension of complex subjects. "Deep HoriXons" represents an ingenious approach to education, combining technology and immersive experiences to prepare students for success in these evolving fields. We will include initial efforts in creating a ChatGPT avatar capability inworld and a 3D virtual AI-powered Command Center demonstrator.
Break
Lunch/Exhibition Break 12:10 PM - 2:00 PM
Session 8:
Cybersecurity and Encryption I
23 April 2024 • 2:00 PM - 3:00 PM EDT | National Harbor 6
Session Chair:
Gabriela Rossi, Datalytica LLC (United States)
13058-24
23 April 2024 • 2:00 PM - 2:20 PM EDT | National Harbor 6
Show Abstract +
Homomorphic encryption is a cryptographic technique that has the potential to significantly impact the field of artificial intelligence (AI). It allows data to be processed in an encrypted form without first decrypting it, thus preserving privacy and security while still enabling meaningful computation. In this talk, we will explore how homomorphic encryption can be used to ensure that data remains encrypted during model updates and aggregation, enhancing privacy.
13058-25
23 April 2024 • 2:20 PM - 2:40 PM EDT | National Harbor 6
Show Abstract +
The internet of things (IoT) and other emerging ubiquitous technologies are supporting the rapid spread of smart systems, which has underlined the need for safe, open, and decentralized data storage solutions. With its inherent decentralization and immutability, blockchain offers itself as a potential solution for these requirements. However, the practicality of incorporating blockchain into real-time sensor data storage systems is a topic that demands in-depth examination. While blockchain promises unmatched data security and auditability, some intrinsic qualities, namely scalability restrictions, transactional delays, and escalating storage demands, impede its seamless deployment in high-frequency, voluminous data contexts typical of real-time sensors. This essay launches a methodical investigation into these difficulties, illuminating their underlying causes, potential effects, and potential countermeasures. In addition, we present a novel pragmatic experimental setup and analysis of blockchain for smart system applications, with an extended discussion of the benefits and disadvantages of deploying blockchain based solutions for smart system ecosystems.
13058-22
23 April 2024 • 2:40 PM - 3:00 PM EDT | National Harbor 6
Show Abstract +
A number of research papers has been published using the architecture of adversarial neural networks to prove that communication between two neural net based on synchronized input can be achieved, and without knowledge of this synchronized information these systems cannot be breached. In this paper we will try to evaluate these adversarial neural net architectures when a third-party gain access to partial secret key, or a noisy secret key, or has knowledge about loss function, or loss values itself, or activation functions used during training of encryption layers. We explore the cryptanalysis side of it in which we will focus on vulnerabilities a neural-net based cryptography network can face. This can be used in future to improve the current neural net-based cryptography architectures. In this paper we show that while the encryption key is necessary to decrypt the messages in neural network domain, the adversarial neural networks can occasionally decrypt messages or raise a concern which will require further training.
Break
Coffee Break 3:00 PM - 3:30 PM
Session 7:
Cybersecurity and Encryption II
23 April 2024 • 4:00 PM - 4:40 PM EDT | National Harbor 6
Session Chair:
Gabriela Rossi, Datalytica LLC (United States)
13058-21
23 April 2024 • 4:00 PM - 4:20 PM EDT | National Harbor 6
Show Abstract +
ISAAC is a 3D-printed pneumatic spacecraft for attitude control system development in a 3-axis gimbal ring. This allows for simulated free-space movement using compressed air as a proxy for cold gas propulsion. The controller is integrated into a website, easycontrols.org, allowing professors, students, and researchers to test and train their control algorithms on real hardware in real time. The entire body and a few components are 3D printed along with the gimbal rings. The website has built-in functions and will have examples, allowing the user to create their algorithm easily. Some examples of proof of concept of this system are the application of a sliding mode controller, using genetic algorithms for PID value tuning, and the application of a simple Neural Network meant to hold orientation all in one axis of gimbal rings.
13058-26
23 April 2024 • 4:20 PM - 4:40 PM EDT | National Harbor 6
Show Abstract +
Zero Trust security is being adopted across companies and government organizations to continually verify cybersecurity requirements. This paper investigates architecture development methodologies that can develop a Zero Trust architecture that implements the missions of an enterprise. An enterprise architecture depends on an organization's strategic priorities and should reflect the organization’s critical decisions. These decisions can be evaluated according to criteria such as interoperability, speed of operations tempo, and cyber-resilience to failures. Zero-Trust architectures must define alternatives tailored to missions. An enterprise architecture can then be developed that describes the context, operations, and resources associated with a strategic implementation decision.
A multi-criteria decision-making method such as the Analytic Hierarchy Process can help guide the development and implementation of Zero Trust strategy. Zero Trust criteria are defined according to quality attributes associated with the DoD Reference Architecture Pillars, and security solutions are evaluated against how well they meet these criteria.
Symposium Plenary on AI/ML + Sustainability
24 April 2024 • 8:30 AM - 10:00 AM EDT | Potomac A
Session Chairs:
Latasha Solomon, DEVCOM Army Research Lab. (United States), Ann Marie Raynal, Sandia National Labs. (United States)
View Full Details: spie.org/dcs/plenary-ai-ml-sustainability
Welcome and opening remarks
24 April 2024 • 8:30 AM - 8:40 AM EDT
Army intelligence data and AI in modern warfare (Plenary Presentation)
Presenter(s): David Pierce, U.S. Army Intelligence (United States)
24 April 2024 • 8:40 AM - 9:20 AM EDT
FUTUR-IC: A three-dimensional optimization path towards building a sustainable microchip industry (Plenary Presentation)
Presenter(s): Anu Agarwal, Massachusetts Institute of Technology, Microphotonics Ctr. and Materials Research Lab. (United States)
24 April 2024 • 9:20 AM - 10:00 AM EDT
Session 10:
Signal Processing and Software Execution Flow
24 April 2024 • 10:30 AM - 11:30 AM EDT | National Harbor 6
Session Chair:
Angela Morales
13058-34
24 April 2024 • 10:30 AM - 10:50 AM EDT | National Harbor 6
Show Abstract +
Neuromorphic architectures are of highly importance in AI/ML to eschew challenges inherent to deep learning acceleration in conventional systems. Throughout the development history of neuromorphic architectures, in-memory computing with emerging memory technologies, such as resistive random-access memory (RRAM), offer advantages by executing operations in situ, exactly where the data are located, leading to significant improvement in data throughput and energy efficiency. In this work, a novel design strategy of memristive-based circuits and systems developed in-house will be demonstrated. Specifically, the prototype is built based upon the hafnium-oxide RRAM in a 6-transistor-1-RRAM (6T1R) structure, supporting bidirectional and high-precision operations for in-situ training without peripherals. Where possible, such computing techniques optimized for AI-enabled cognitive operations offer faster yet more efficient decision-making to enable warfighter success.
13058-35
24 April 2024 • 10:50 AM - 11:10 AM EDT | National Harbor 6
Show Abstract +
The OpenMutt platform is a modular, robotic quadruped capable of being used as a testbed for a variety of research opportunities increasing multidisciplinary research. The OpenMutt quadruped allows for a low-cost testbed for actuator drive design, biomimicry, and instrumentation. The current design is meant to be modular and built upon to facilitate these research disciplines with the usage of a robust 13:1 cycloidal actuator, modular feet, and multiple mounting points for passive control surfaces and instrumentation.
13058-19
24 April 2024 • 11:10 AM - 11:30 AM EDT | National Harbor 6
Show Abstract +
Traditional classroom teachings use 2-D illustrations for 3-D spacecraft dynamics, making real-world applications hard for students. Our project develops CubeSat testbeds in 1U, 3U, and 6U sizes, utilizing reaction wheels on each axis for precise attitude control. These testbeds, housed in actively driven gimbal rings to offset gravitational effects providing an environment analogous to microgravity, enable users to experiment with diverse control systems, from PID controllers to advanced model predictive controls. The platform serves as both an educational tool and a research apparatus. Our vision is a dedicated website where users can upload and live-stream their control algorithms in action, fostering a global collaboration and deepening understanding of spacecraft control dynamics.
Break
Coffee Break 10:00 AM - 10:30 AM
DECEIVER Session Kickoff
24 April 2024 • 12:50 PM - 1:05 PM EDT | National Harbor 6
Session Chair:
Yu Chen, Binghamton Univ. (United States)
Under the umbrella of Disruptive Technologies in Information Sciences VIII, we organize this session for detecting and deterring misinformation and deception focusing on disseminating education on counteracting erroneous information, verifying evidence, and reporting (DECEIVER). The DECEIVER session aims at bringing researchers and experts together to present and discuss the latest developments and technical solutions concerning various aspects of rebuilding a trust foundation in the era of rumor, misinformation, and disinformation.
Break
Lunch/Exhibition Break 11:30 AM - 12:50 PM
Session 11:
DECEIVER I
24 April 2024 • 1:05 PM - 3:05 PM EDT | National Harbor 6
Session Chair:
Yu Chen, Binghamton Univ. (United States)
13058-36
The impact of misinformation on the health of underrepresented youth during public health crises: a preliminary study
(Invited Paper)
24 April 2024 • 1:05 PM - 1:35 PM EDT | National Harbor 6
Show Abstract +
The digital age has brought unprecedented access to information, but it has also ushered in a formidable challenge — misinformation. Amidst the wealth of research on the societal, political, and economic repercussions of misinformation, one crucial aspect remains underexplored: its profound impact on the mental health of the young generation. This paper aims to address this critical gap by conducting a comprehensive survey of the threats posed by misinformation to the mental well-being of young individuals.
13058-37
Uncovering deep-rooted cultural differences (UNCOVER)
(Invited Paper)
24 April 2024 • 1:35 PM - 2:05 PM EDT | National Harbor 6
Show Abstract +
This study delves into the interconnected realms of Debates, Fake News, and Propaganda, with an emphasis on discerning prominent ideological underpinnings distinguishing Russian from English authors. Leveraging the advanced capabilities of Large Language Models (LLMs), particularly GPT-4, we process and analyze a large corpus of over 80,000 Wikipedia articles to unearth significant insights. Despite the inherent linguistic distinctions between Russian and English texts, our research highlights the adeptness of LLMs in bridging these variances. Our approach, includes translation, question generation and answering, along with emotional analysis, to probe the gathered information. A ranking metric based on the emotional content is used to assess the impact of our approach. Furthermore, our research identifies important limitations within existing data resources for propaganda identification. To address these challenges and foster future research, we present a curated synthetic dataset designed to encompass a diverse spectrum of topics and achieve balance across various propaganda types.
13058-38
Debunking warfare narratives: the role of commercial satellites in the Russian-Ukrainian conflict
(Invited Paper)
24 April 2024 • 2:05 PM - 2:35 PM EDT | National Harbor 6
Show Abstract +
Over the past three decades, information warfare has emerged as a critical component of international conflict. With the proliferation of technology and media networks, various stakeholders have exploited their capabilities to manipulate public perception. The ongoing Russo-Ukrainian conflict underscores the potency of these tactics, as they deepen societal divides and obstruct efforts at conflict resolution. Disinformation spans a wide gamut, from denials of human rights abuses to personal defamation. A primary challenge in countering disinformation lies in its tenacity, bolstered by confirmation bias—a tendency to dismiss evidence that contradicts existing beliefs. Against this backdrop, we delve into the potential of commercial satellites, which operate outside of state domains, as a means of countering falsehoods through textual and visual evidence. Utilizing an online survey targeting citizens in Russia and Ukraine, we assess the impact of disinformation campaigns on attitudes towards the war and its leaders and evaluate the efficacy of commercial satellites as a debunking instrument.
13058-39
A lightweight deep learning model for rapid detection of fabricated ENF signals from audio sources
(Invited Paper)
24 April 2024 • 2:35 PM - 3:05 PM EDT | National Harbor 6
Show Abstract +
Being aware of the application of Electrical Network Frequency (ENF) for multimedia data authentication, attackers may embed fake ENF signals in their content to fool the detector. In this paper, we investigate a computationally efficient deep learning model to quickly detect potential fabrications in ENF signals from numerous audio sources. The model is derived through a combination of spectrogram analysis techniques and image-based anomaly detection, enabling it to discern alterations in ENF signals, making it a potential tool for multimedia data authenticity verification.
Session 12:
DECEIVER II
24 April 2024 • 3:25 PM - 5:35 PM EDT | National Harbor 6
Session Chair:
Yu Chen, Binghamton Univ. (United States)
13058-40
Generative adversarial networks-based AI-generated imagery authentication using frequency domain analysis
(Invited Paper)
24 April 2024 • 3:25 PM - 3:55 PM EDT | National Harbor 6
Show Abstract +
In an era characterized by the prolific generation of digital imagery through advanced artificial intelligence, the need for reliable methods to authenticate actual photographs from AI-generated ones has become paramount. This paper delves into the imperative task of imagery authentication and introduces a novel approach harnessing the power of Generative Adversarial Networks (GANs) and Frequency Domain Analysis.
13058-41
Video modification in drone and satellite imagery
(Invited Paper)
24 April 2024 • 3:55 PM - 4:25 PM EDT | National Harbor 6
Show Abstract +
The ability to create and detect synthetic video is becoming critically important to scene understanding. Specifically, it may be desirable to add, remove, or modify vehicles in satellite and overhead video. We present an extension of our previous work in static imagery to video sequences from drone and satellite footage. Amongst other architectures, different generative adversarial network (GANs) variations are employed, including fully dynamic 3D convolutional networks and interframe “warp” prediction. A separate interframe consistency classifier is also leveraged. We run experiments on a real-world dataset, presenting promising results in terms of FID, KID, and metrics developed from a classifier trained on our dataset.
13058-42
Integrating information warfare strategies with emerging AI technologies for enhanced national security
(Invited Paper)
24 April 2024 • 4:25 PM - 4:55 PM EDT | National Harbor 6
Show Abstract +
As the landscape of global conflict evolves, the integration of Information Warfare (IW) strategies with emerging technologies like Artificial Intelligence (AI) becomes increasingly crucial for national security. This presentation, led by Terry Traylor, a seasoned military professional with expertise in IW and AI, aims to explore the synergies between these domains. Drawing from his experience as Deputy G39 for Information Warfare at MARSOC and his academic background in computer science focusing on machine learning, the talk will delve into the challenges and opportunities of incorporating AI into IW operations. Special attention will be given to the ethical considerations of AI in IW and how machine learning can be leveraged to counter disinformation campaigns effectively. The session will also discuss a case study involving a Phase II SBIR for USSOCOM, emphasizing the practical applications of these integrations in real-world scenarios. This presentation aims to provide a comprehensive understanding of how AI can augment IW strategies, offering a forward-looking perspective on national security.
13058-32
24 April 2024 • 4:55 PM - 5:15 PM EDT | National Harbor 6
Show Abstract +
Continuous time digital signal processing has the potential of being disruptive in three engineering disciplines: digital signal processing, control systems, and compressive sensing.
For conventional digital signal processing (DSP), the signal-to-distortion-and-noise ratio (SINAD) significantly degrades for weak signals. The best SINAD occurs when the input signal completely fills the input amplitude range for an analog-to-digital converter. For continuous time (CT) digital signal processing (DSP), Tsividis shows ~100 dB SINAD for a 16-voltage level analog-to-digital converter (ADC) for offline signal reconstruction [1]. Tsividis’ research appears to show that CT-DSP’s SINAD does significantly degrade for weak signals. It is believed that for signals close to one voltage level, the SINAD will degrade; however, the SINAD will still be much better than conventional DSP.
13058-148
24 April 2024 • 5:15 PM - 5:35 PM EDT | National Harbor 6
Show Abstract +
According to Executive Order 14110 emphasizing the safe, secure, and trustworthy advancement and utilization of artificial intelligence, it mandates conducting research, development and deployment with a strong emphasis on ethical practices. The United States’ Department of Defense (DoD) and numerous commercial industries require a robust methodology to test their AI/ML models, ensuring regulatory compliance while safeguarding the security and intellectual property of their models. Reverse Engineering and Vulnerability Elucidation of ALgorithms (REVEAL) is a groundbreaking invention which is designed to enable the reverse engineering and characterization of AI/ML algorithms without access to the underlying code base. With this type of “blackbox assessment”, REVEAL will provide a method to enumerate the security and robustness of various AI enabled systems. It will allow developers to improve models, provide new strategies for test and evaluation, and help ensure comprehensive adherence to governmental regulations.
Break
Coffee Break 3:05 PM - 3:25 PM
Panel Discussion: DECEIVER
24 April 2024 • 5:45 PM - 6:15 PM EDT | National Harbor 6
Human society is facing an unprecedented era of information bombardment. Every day we are swamped by such a huge number of texts, videos, audio, emails, and posts that are far beyond what one can digest. The Internet and the social media are key game-changers in exploiting rights and freedoms. They give the opportunity for spreading limitless fake photos, reports, and opinions. Recent deepfake video attacks on some public scenarios have raised more concerns. Misinformation may actually cause disturbance in our society and ruin the foundation of trust. Government agencies like the U.S. Defense Advanced Research Projects Agency (DARPA) and National Security Agency (NSA) are concerned about losing the war against misinformation that uses popular ML techniques to automatically incorporate artificial components into existing video streams. Join this panel discussion on DECEIVER: Disseminating, Education on Counteracting, Erroneous, Information, Verifying, Evidence, and Reporting, to learn about detecting and deterring misinformation and deception, and hear researchers and experts discuss the latest developments and technical solutions concerning various aspects of rebuilding a trust foundation in the era of rumor, misinformation, and disinformation.
Digital Posters
The posters listed below are available exclusively for online viewing during the week of SPIE Defense + Commercial Sensing 2024.
13058-43
On demand | Presenting live 25 April 2024
Show Abstract +
This paper gives a bibliometric summary of Unscented Kalman Filter (UKF) in AI-infused robotics, highlighting its role in unifying control and cognition. Using a systematic approach that includes literature collection from IEEE Xplore, Web of Science and Google Scholar, rigorous screening and selection, and VOSviewer for a comprehensive bibliometric analysis. This analysis reports major trends, primary contributors and central themes, highlighting UKF’s pivotal role in improving robotics cognitive and control capacities. The study emphasizes the universally used UKF in many fields of robotics, i.e. in navigation and mapping, sensor fusion, and state estimation, as one of its principal developers, which illustrates its vital role in promoting robotic autonomy and intelligence. The integration of findings from the bibliometric analysis thus not only presents the current state of research but also identifies possible future research directions, highlighting the increasing unification of control theories and cognitive processes in robotics. This research adds to the body of knowledge by delivering a comprehensive map of the UKF application.
13058-44
On demand | Presenting live 25 April 2024
Show Abstract +
In recent years, the interest in Software-Defined Networking (SDN) has been very high. Many applications of traditional networking have been implemented in SDN environments in order to test the performance of the different network devices. In this paper, server load-balancing (LB) based on SDN has been developed and tested in order to verify the effectiveness of this approach inside the new networking approach. In our implementation, we have used a Ruy controller for controlling and managing network devices and two different LB algorithms have been implemented. We have performed an analysis of these two algorithms with a system without load balancing in a server-client system changing the number of servers and clients in order to show the performance of the SDN network.
13058-45
On demand | Presenting live 25 April 2024
Show Abstract +
The air pollution, with its impacts on human health and the environment, is a growing global issue. In this article, we propose the implementation of a Multi-Interface Mobile Gateway (MIMG) with LPWAN technology in public transportation vehicles for monitoring air quality. The idea is to use a mobile monitoring system that can reduce the cost of the classical fixed air pollution and environmental monitoring stations. This approach addresses challenges such as data transfer, interference, and data pre-processing to reduce the amount of data sent over the remote data management center. We conducted a system emulation to evaluate some data forwarding strategies and to evaluate the overall traffic load generated by the mobile station over the overall network. Furthermore, the MIMG manages the use of the communication interface, uses data aggregation techniques to reduce the amount of data to be transmitted, and utilizes machine learning to enhance the accuracy of the low-cost sensor readings. Our approach has significant applications in urban air quality management.
Panel Discussion: Keeping National Security AI Trustworthy
25 April 2024 • 11:00 AM - 12:00 PM EDT | Prince George Exhibition Hall, Industry Stage
This panel discussion will explore some of the ethical quandaries and hazards AI-assisted technologies present for national security/defense, including on the battlefield in active conflicts. Many of these capabilities are offered as contract services to militaries, adding another layer of complexity to issues that must be managed to leverage the success promised by AI.
Topics the panel will include:
MENU: Coffee and tea service available nearby.
SETUP: Stage and theater style seating. .
Topics the panel will include:
- Who controls access to private satellite data?
- Hallucinations and AI risk management
- Lethal decision-making by AI machines
- Fighting AI disinformation in global conflict
- Trustworthiness of datasets
Moderator
 |
|
 |
|
 |
|
Event Details
FORMAT: Panel discussion followed by audience Q&A.MENU: Coffee and tea service available nearby.
SETUP: Stage and theater style seating. .
Program Committee
Program Committee