搜索结果：army

In recent years, the widespread adoption of Large Language Models (LLMs) has sparked interest in their potential for application within the military domain. However, the current generation of LLMs demonstrate sub-optimal performance on Army use cases, due to the prevalence of domain-specific vocabulary and jargon. In order to fully leverage LLMs in-domain, many organizations have turned to fine-tuning to circumvent the prohibitive costs involved in training new LLMs from scratch. In light of this trend, we explore the viability of adapting open-source LLMs for usage in the Army domain in order to address their existing lack of domain-specificity. Our investigations have resulted in the creation of three distinct generations of TRACLM, a family of LLMs fine-tuned by The Research and Analysis Center (TRAC), Army Futures Command (AFC). Through continuous refinement of our training pipeline, each successive iteration of TRACLM displayed improved capabilities when applied to Army tasks and use cases. Furthermore, throughout our fine-tuning experiments, we recognized the need for an evaluation framework that objectively quantifies the Army domain-specific knowledge of LLMs. To address th

Unmanned Vehicles (UxVs) are increasingly used in modern military operations for reconnaissance, surveillance, and strike missions, enhancing situational awareness while reducing risk to personnel. Their affordability and rapid deployment have encouraged the adoption of commercial solutions. However, many rely on insecure protocols such as MAVLink, which lack authentication and encryption mechanisms. This paper designed, implemented, and evaluated a new secure command-and-control architecture that ensures confidentiality, integrity, and authentication (CIA) while supporting real-time control delegation between Ground Control Stations (GCSs). The proposed solution, named New Command and Control System (NC2S), enforces a zero-trust model integrating hierarchical credential-based privileges to regulate access and control among Tactical Commanders (TC), GCSs, and UxVs. It employs mutual Transport Layer Security (mTLS) with Elliptic Curve Digital Signature Algorithm (ECDSA) certificates and Elliptic Curve Diffie-Hellman (ECDH) key exchange, while message integrity is ensured through Hash-based Message Authentication Codes (HMAC). Multiple lightweight protocols were developed for credent

Vision Foundation Models (VFMs) have demonstrated outstanding performance on numerous downstream tasks. However, due to their inherent representation biases originating from different training paradigms, VFMs exhibit advantages and disadvantages across distinct vision tasks. Although amalgamating the strengths of multiple VFMs for downstream tasks is an intuitive strategy, effectively exploiting these biases remains a significant challenge. In this paper, we propose a novel and versatile "Swiss Army Knife" (SAK) solution, which adaptively distills knowledge from a committee of VFMs to enhance multi-task learning. Unlike existing methods that use a single backbone for knowledge transfer, our approach preserves the unique representation bias of each teacher by collaborating the lightweight Teacher-Specific Adapter Path modules with the Teacher-Agnostic Stem. Through dynamic selection and combination of representations with Mixture-of-Representations Routers, our SAK is capable of synergizing the complementary strengths of multiple VFMs. Extensive experiments show that our SAK remarkably outperforms prior state of the arts in multi-task learning by 10% on the NYUD-v2 benchmark, while

IMPORTANCE: The Army Study to Assess Risk and Resilience in Servicemembers (Army STARRS) is a multicomponent study designed to generate actionable recommendations to reduce Army suicides and increase knowledge of risk and resilience factors for suicidality. OBJECTIVES: To present data on prevalence, trends, and basic sociodemographic and Army experience correlates of suicides and accident deaths among active duty Regular Army soldiers between January 1, 2004, and December 31, 2009, and thereby establish a foundation for future Army STARRS investigations. DESIGN, SETTING, AND PARTICIPANTS: Analysis of trends and predictors of suicide and accident deaths using Army and Department of Defense administrative data systems. Participants were all members of the US Regular Army serving at any time between 2004 and 2009. MAIN OUTCOMES AND MEASURES: Death by suicide or accident during active Army service. RESULTS: The suicide rate rose between 2004 and 2009 among never deployed and currently and previously deployed Regular Army soldiers. The accident death rate fell sharply among currently deployed soldiers, remained constant among the previously deployed, and trended upward among the never deployed. Increased suicide risk was associated with being a man (or a woman during deployment), white race/ethnicity, junior enlisted rank, recent demotion, and current or previous deployment. Sociodemographic and Army experience predictors were generally similar for suicides and accident deaths. Time trends in these predictors and in the Army's increased use of accession waivers (which relaxed some qualifications for new soldiers) do not explain the rise in Army suicides. CONCLUSIONS AND RELEVANCE: Predictors of Army suicides were largely similar to those reported elsewhere for civilians, although some predictors distinct to Army service emerged that deserve more in-depth analysis. The existence of a time trend in suicide risk among never-deployed soldiers argues indirectly against the view that exposure to combat-related trauma is the exclusive cause of the increase in Army suicides.

We present the proof-of-concept for minimalist market design (Sönmez, 2023) as an effective methodology to enhance an institution based on the desiderata of stakeholders with minimal interference. Four objectives-respecting merit, increasing retention, aligning talent, and enhancing trust-guided reforms to US Army's centralized branching process of cadets to military specialties since 2006. USMA's mechanism for the Class of 2020 exacerbated challenges implementing these objectives. Formulating the Army's desiderata as rigorous axioms, we analyze their implications. Under our minimalist approach to institution redesign, the Army's objectives uniquely identify a branching mechanism. Our design is now adopted at USMA and ROTC.

We present OpenMU-Bench, a large-scale benchmark suite for addressing the data scarcity issue in training multimodal language models to understand music. To construct OpenMU-Bench, we leveraged existing datasets and bootstrapped new annotations. OpenMU-Bench also broadens the scope of music understanding by including lyrics understanding and music tool usage. Using OpenMU-Bench, we trained our music understanding model, OpenMU, with extensive ablations, demonstrating that OpenMU outperforms baseline models such as MU-Llama. Both OpenMU and OpenMU-Bench are open-sourced to facilitate future research in music understanding and to enhance creative music production efficiency.

As one of the most crucial scenarios of the Internet of Things (IoT), wireless multimedia sensor networks (WMSNs) pay more attention to the information-intensive data (e.g., audio, video, image) for remote environments. The area coverage reflects the perception of WMSNs to the surrounding environment, where a good coverage effect can ensure effective data collection. Given the harsh and complex physical environment of WMSNs, which easily form the sensing overlapping regions and coverage holes by random deployment. The intention of our research is to deal with the optimization problem of maximizing the coverage rate in WMSNs. By proving the NP-hard of the coverage enhancement of WMSNs, inspired by the predation behavior of army ants, this article proposes a novel swarm intelligence (SI) technology army ant search optimizer (AASO) to solve the above problem, which is implemented by five operators: army ant and prey initialization, recruited by prey, attack prey, update prey, and build ant bridge. The simulation results demonstrate that the optimizer shows good performance in terms of exploration and exploitation on benchmark suites when compared to other representative SI algorithms.

Machine Learning (ML) models become vulnerable to Model Stealing Attacks (MSA) when they are deployed as a service. In such attacks, the deployed model is queried repeatedly to build a labelled dataset. This dataset allows the attacker to train a thief model that mimics the original model. To maximize query efficiency, the attacker has to select the most informative subset of data points from the pool of available data. Existing attack strategies utilize approaches like Active Learning and Semi-Supervised learning to minimize costs. However, in the black-box setting, these approaches may select sub-optimal samples as they train only one thief model. Depending on the thief model's capacity and the data it was pretrained on, the model might even select noisy samples that harm the learning process. In this work, we explore the usage of an ensemble of deep learning models as our thief model. We call our attack Army of Thieves(AOT) as we train multiple models with varying complexities to leverage the crowd's wisdom. Based on the ensemble's collective decision, uncertain samples are selected for querying, while the most confident samples are directly included in the training data. Our ap

Coverage of interest points is one of the most critical issues in directional sensor networks. However, considering the remote or inhospitable environment and the limitation of the perspective of directional sensors, it is easy to form perception blind after random deployment. The intension of our research is to deal with the bound-constrained optimization problem of maximizing the coverage of target points. A coverage enhancement strategy based on a discrete army ant search optimizer (DAASO) is proposed to solve the above problem, which is inspired by the biological habits of army ants. A set of experiments are conducted using different sensor parameters. Experimental results verify the effectiveness of the DAASO in coverage effect when compared to the existing methods.

UNLABELLED: IMPORTANCE/OBJECTIVE: Although the suicide rate in the U.S. Army has traditionally been below age-gender matched civilian rates, it has climbed steadily since the beginning of the Iraq and Afghanistan conflicts and since 2008 has exceeded the demographically matched civilian rate. The Army Study to Assess Risk and Resilience in Servicemembers (Army STARRS) is a multicomponent epidemiological and neurobiological study designed to generate actionable evidence-based recommendations to reduce Army suicides and increase knowledge about risk and resilience factors for suicidality and its psychopathological correlates. This paper presents an overview of the Army STARRS component study designs and of recent findings. DESIGN/SETTING/PARTICIPANTS/INTERVENTION: Army STARRS includes six main component studies: (1) the Historical Administrative Data Study (HADS) of Army and Department of Defense (DoD) administrative data systems (including records of suicidal behaviors) for all soldiers on active duty 2004-2009 aimed at finding administrative record predictors of suicides; (2) retrospective case-control studies of fatal and nonfatal suicidal behaviors (each planned to have n = 150 cases and n = 300 controls); (3) a study of new soldiers (n = 50,765 completed surveys) assessed just before beginning basic combat training (BCT) with self-administered questionnaires (SAQ), neurocognitive tests, and blood samples; (4) a cross-sectional study of approximately 35,000 (completed SAQs) soldiers representative of all other (i.e., exclusive of BCT) active duty soldiers; (5) a pre-post deployment study (with blood samples) of soldiers in brigade combat teams about to deploy to Afghanistan (n = 9,421 completed baseline surveys), with sub-samples assessed again one, three, and nine months after returning from deployment; and (6) a pilot study to follow-up SAQ respondents transitioning to civilian life. Army/DoD administrative data are being linked prospectively to the large-scale survey samples to examine predictors of subsequent suicidality and related mental health outcomes. MAIN OUTCOME MEASURES: Measures (self-report and administratively recorded) of suicidal behaviors and their psychopathological correlates. RESULTS: Component study cooperation rates are comparatively high. Sample biases are relatively small. Inefficiencies introduced into parameter estimates by using nonresponse adjustment weights and time-space clustering are small. Initial findings show that the suicide death rate, which rose over 2004-2009, increased for those deployed, those never deployed, and those previously deployed. Analyses of administrative records show that those deployed or previously deployed were at greater suicide risk. Receiving a waiver to enter the Army was not associated with increased risk. However, being demoted in the past two years was associated with increased risk. Time in current deployment, length of time since return from most recent deployment, total number of deployments, and time interval between most recent deployments (known as dwell time) were not associated with suicide risk. Initial analyses of survey data show that 13.9% of currently active non-deployed regular Army soldiers considered suicide at some point in their lifetime, while 5.3% had made a suicide plan, and 2.4% had attempted suicide. Importantly, 47-60% of these outcomes first occurred prior to enlistment. Prior mental disorders, in particular major depression and intermittent explosive disorder, were the strongest predictors of these self-reported suicidal behaviors. Most onsets of plans-attempts among ideators (58.3-63.3%) occurred within the year of onset of ideation. About 25.1% of non-deployed U.S. Army personnel met 30-day criteria for a DSM-IV anxiety, mood, disruptive behavior, or substance disorder (15.0% an internalizing disorder; 18.4% an externalizing disorder) and 11.1% for multiple disorders. Importantly, three-fourths of these disorders had pre-enlistment onsets. CONCLUSIONS: Integration across component studies creates strengths going well beyond those in conventional applications of the same individual study designs. These design features create a strong methodological foundation from which Army STARRS can pursue its substantive research goals. The early findings reported here illustrate the importance of the study and its approach as a model of studying rare events particularly of national security concern. Continuing analyses of the data will inform suicide prevention for the U.S. Army.

Despite its long history, the classical game of peg solitaire continues to attract the attention of the scientific community. In this paper, we consider two problems with an algorithmic flavour which are related with this game, namely Solitaire-Reachability and Solitaire-Army. In the first one, we show that deciding whether there is a sequence of jumps which allows a given initial configuration of pegs to reach a target position is NP-complete. Regarding Solitaire-Army, the aim is to successfully deploy an army of pegs in a given region of the board in order to reach a target position. By solving an auxiliary problem with relaxed constraints, we are able to answer some open questions raised by Csákány and Juhász (Mathematics Magazine, 2000). To appreciate the combinatorial beauty of our solutions, we recommend to visit the gallery of animations provided at http://solitairearmy.isnphard.com.

This paper provides an overview of research programs in cyber security performed by the U.S Army Research Laboratory. Although ARL is the U.S. Army's corporate laboratory that focuses on fundamental and early applied research, the fundamental science endeavors are closely integrated with extensive operationally-oriented programs. One example is the Cyber Collaborative Research Alliance (CRA) that brings together ARL scientists with academic researchers from dozens of U.S. universities. ARL cyber scientists are largely driven by challenges unique to the ground operations of the Army; this paper outlines a few of these challenges and the ways in which they are addressed by ARL research efforts. The long-term campaign of cyber research is guided by the vision of the future Army battlefield. In the year 2040, it will be a highly converged virtual-physical space, where cyber operations will be an integral part of the battle.

In this working paper we explore the use of an NLP system to assist the work of Security Force Monitor (SFM). SFM creates data about the organizational structure, command personnel and operations of police, army and other security forces, which assists human rights researchers, journalists and litigators in their work to help identify and bring to account specific units and personnel alleged to have committed abuses of human rights and international criminal law. This working paper presents an NLP system that extracts from English language news reports the names of security force units and the biographical details of their personnel, and infers the formal relationship between them. Published alongside this working paper are the system's code and training dataset. We find that the experimental NLP system performs the task at a fair to good level. Its performance is sufficient to justify further development into a live workflow that will give insight into whether its performance translates into savings in time and resource that would make it an effective technical intervention.

The solitaire army is a one-person peg jumping game where a player attempts to advance an "army" of pegs as far as possible into empty territory. The game was introduced by John Conway and is also known as "Conway's Soldiers". We consider various generalizations of this game in different 2D geometries, unify them under a common mathematical framework, and find the minimum size army capable of advancing a given number of steps.