USMA Digital Commons (United States Military Academy, West Point)
Not a member yet
1355 research outputs found
Sort by
USCG Retention Study
Full text linkThe U.S. Coast Guard Retention Study is a comprehensive exploration of the findings in the 2019 Research and Development (RAND) Coast Guard Women’s Retention Study. The Retention Study Capstone team developed a survey based off of the findings from the 2019 RAND Study. The retention survey asks Coast Guard members about factors that impact(ed) their decision to remain in the Coast Guard. The retention survey launched for the third time during the Spring of 2023.
This Retention Study was conducted in partnership with the Women’s Leadership Institute (WLI) and the USCG Alumni Association in order to utilize USCG alumni networking channels to both distribute and promote the retention survey. For the first time, the retention survey expanded its participants from exclusively reservists to Coast Guard retirees, active-duty members, and separated members.
Unlike in previous studies, the 2023 Retention Capstone team utilized statistics in order to identify the key factors influencing gender inequality in Coast Guard retention rates. After cleaning the Likert survey data, two-tailed t-tests and ridit analysis, a non-parametric statistical test for ordinal, categorical data, were used to compare women’s and men’s responses for each survey question. In the retention factors category, we found that statistically, women are more likely to stay in the Coast Guard, when compared to men, due to benefits related to healthcare, retirement, and education, financial independence the desire to be a role model for others, and the desire to increase the diversity of leaders in the Coast Guard. Conversely, we found that men are statistically more likely to stay in the Coast Guard, when compared to women, due to enjoyment of the mission and work, and positive associations with people in the Coast Guard. Additionally, these statistical tests found that for every question asked to both women and men in the work environmental factors category, which is comprised of leadership, body composition standards, gender bias and discrimination, and perceived sexual assault and harassment, women were statistically more likely to leave the Coast Guard than men, showing the gender inequality in retention rates in the Coast Guard
Data-Efficient, Federated Learning for Raw Network Traffic Detection
Full text linkTraditional machine learning (ML) models used for enterprise network intrusion detection systems (NIDS) typically rely on vast amounts of centralized data with expertly engineered features. Previous work, however, has shown the feasibility of using deep learning (DL) to detect malicious activity on raw network traffic payloads rather than engineered features at the edge, which is necessary for tactical military environments. In the future Internet of Battlefield Things (IoBT), the military will find itself in multiple environments with disconnected networks spread across the battlefield. These resource-constrained, data-limited networks require distributed and collaborative ML/DL models for inference that are continually trained both locally, using data from each separate tactical edge network, and then globally in order to learn and detect malicious activity represented across the multiple networks in a collaborative fashion. Federated Learning (FL), a collaborative paradigm which updates and distributes a global model through local model weight aggregation, provides a solution to train ML/DL models in NIDS utilizing learning from multiple edge devices from the disparate networks without the sharing of raw data. We develop and experiment with a data-efficient, FL framework for IoBT settings for intrusion detection using only raw network traffic in restricted, resource-limited environments. Our results indicate that regardless of the DL model architecture used on edge devices, the Federated Averaging FL algorithm achieved over 93% accuracy in model performance in detecting malicious payloads after only five episodes of FL training
Autonomous Cyber Warfare Agents: Dynamic Reinforcement Learning for Defensive Cyber Operations
Full text linkIn this work, we aim to develop novel cybersecurity playbooks by exploiting dynamic reinforcement learning (RL) methods to close holes in the attack surface left open by the traditional signature-based approach to Defensive Cyber Operations (DCO). A useful first proof-of-concept is provided by the problem of training a scanning defense agent using RL; as a first line of defense, it is important to protect sensitive networks from network mapping tools. To address this challenge, we developed a hierarchical, Monte Carlo-based RL framework for the training of an autonomous agent which detects and reports the presence of Nmap scans in near real-time, efficiently and with near-perfect accuracy. Our algorithm is powered by a reduction of the state space given by a transformer, CLAPBAC, an anomaly detection tool which applies natural language processing to cybersecurity in a manner consistent with state-of-the-art. In a realistic scenario emulated in CyberVAN, our approach generates optimized playbooks for effective defense against malicious insiders inappropriately probing sensitive networks
