Publication Notices

Notifications of the Newest Publications and Reports Released by ERDC

Contact ERDC Library

erdclibrary@ask-a-librarian.info

601.501.7632 - text
601.634.2355 - voice

 

ERDC Library Catalog

Not finding what you are looking for? Search the ERDC Library Catalog!

Results:
Category: Publications: Geospatial Research Laboratory (GRL)
Clear
  • Adversarial Artificial Intelligence: Implications for Military Operations

    Introduction: Artificial intelligence and machine learning algorithms are at the forefront of current research to help military analysts deal with triaging ever larger amounts of data from deployed sensors. These automated approaches will become increasingly embedded into the military decision making process, which makes it crucial to understand how these algorithms generate outputs and how sensitive they are to perturbations during training or classification. In other words, humans must have a ‘theory of mind’ for these sets of approaches in order to begin to trust them enough to make life or death decisions. Research in this area is known as adversarial examples for artificial intelligence / machine learning. Previous works in this domain focused on degrading classification performance with respect to added noise to new data. Some of these works achieved notable results on image data by subtly increasing noise, such that the image appeared unaltered to the human eye, but significantly impacted performance (Athalye et al. 2017). Povolny and Trivedi (2020) achieved similar results, but made a small visually obvious change to induce a degradation in performance. One notable work examined the effects of an increase in physical scale of the sensed environment (such as the large areas recorded for remote sensing platforms) on adversarial perturbations (Czaja et al. 2018). This technical note (TN) describes an initial foray into understanding how physical changes to the appearance of military vehicles resulted in performance degradation for a convolutional neural network (CNN). The military vehicles chosen were the M2 Bradley Infantry Fighting Vehicle and the M1064 Mortar Carrier. As stand-ins for the actual vehicle, plastic scale models were used, each a 1/35 scale replica. The results of this research have yielded a curated training and test data set of images related to the M2 and M1064, trained models based on a combined ResNet / Inception implementation from the Keras project, and adversarial examples mocked up using the scale models with images taken by a smartphone.
  • Energy Atlas—Mapping Energy-Related Data for DoD Lands in Alaska: Phase 2—Data Expansion and Portal Development

    ABSTRACT: As the largest Department of Defense (DoD) land user in Alaska, the U.S. Army oversees over 600,000 hectares of land, including remote areas accessible only by air, water, and winter ice roads. Spatial information related to the energy resources and infrastructure that exist on and adjacent to DoD installations can help inform decision makers when it comes to installation planning. The Energy Atlas−Alaska portal provides a secure value-added resource to support the decision-making process for energy management, investments in installation infrastructure, and improvements to energy resiliency and sustainability. The Energy Atlas–Alaska portal compiles spatial information and provides that information through a secure online portal to access and examine energy and related resource data such as energy resource potential, energy corridors, and environmental information. The information database is hosted on a secure Common Access Card–authenticated portal that is accessible to the DoD and its partners through the Army Geospatial Center’s Enterprise Portal. This Enterprise Portal provides effective visualization and functionality to support analysis and inform DoD decision makers. The Energy Atlas–Alaska portal helps the DoD account for energy in contingency planning, acquisition, and life-cycle requirements and ensures facilities can maintain operations in the face of disruption.