The high mobility of Army tactical networks, combined with their close proximity to hostile actors, elevates the risks associated with short-range network attacks. The connectivity model for such short range connections under active operations is extremely fluid, and highly dependent upon the physical space within which the element is operating, as well as the patterns of movement within that space. To handle these dependencies, we introduce the notion of "key cyber-physical terrain": locations within an area of operations that allow for effective control over the spread of proximity-dependent malware in a mobile tactical network, even as the elements of that network are in constant motion with an unpredictable pattern of node-to-node connectivity. We provide an analysis of movement models and approximation strategies for finding such critical nodes, and demonstrate via simulation that we can identify such key cyber-physical terrain quickly and effectively.
Crown Jewels Analysis using Reinforcement Learning with Attack Graphs
Deloitte Consulting, LLC（德勤咨询有限责任公司）；Hume Center for National Security and Technology, Virginia Polytechnic University（弗吉尼亚理工大学休姆国家安全与技术中心）；Deloitte & Touche LLP（德勤会计师事务所）
A Data-Driven Predictive Analysis on Cyber Security Threats with Key Risk Factors
University of Chittagong（吉大港大学）；Northwestern Polytechnical University（西北工业大学）；Noakhali Science and Technology University（诺阿卡利科技大学）；Chittagong University of Engineering & Technology（吉大港工程技术大学）；Edith Cowan University（伊迪斯科文大学）
本文针对网络风险预测问题，提出一种基于 Pertinent Features 随机森林的机器学习模型，结合问卷数据增强和 Apriori 关联规则分析，在20个特征下实现95.95%的准确率，有效识别网络攻击受害者及关键风险因素。
Artificial Neural Network for Cybersecurity: A Comprehensive Review
网络安全是一个非常新兴的领域，可以保护系统、网络和数据免受数字攻击。随着互联网规模的增加和网络攻击的演变，开发新的网络安全工具变得非常重要，特别是对于物联网（IoT）网络。本文对深度学习（DL）方法在网络安全中的应用进行了系统的综述。本文简要介绍了用于网络安全的深度学习方法，包括深度信念网络、生成对抗网络、递归神经网络等。接下来，我们将说明浅层学习和深度学习之间的区别。此外，还讨论了物联网和其他网络中当前流行的网络攻击，以及DL方法管理这些攻击的有效性。此外，本文还介绍了重点介绍DL技术、网络安全应用和数据集来源的研究。接下来，讨论DL系统用于恶意软件检测和分类、入侵检测和其他频繁的网络攻击（包括识别文件类型、垃圾邮件和网络流量）的可行性。我们的综述表明，当应用于自定义数据集时，受限玻尔兹曼机（RBM）获得了99.72%的高分类准确率，而长短期记忆（LSTM）在KDD Cup 99数据集上达到了99.80%的准确率。最后，本文讨论了网络安全对于可靠和实用的物联网驱动的医疗保健系统的重要性。
Leveraging Large Language Models for Cybersecurity Risk Assessment -- A Case from Forestry Cyber-Physical Systems
Chalmers University of Technology（楚德斯技术大学）；University of Gothenburg（哥德堡大学）；Carnegie Mellon University（卡内基梅隆大学）；RISE Research Institutes of Sweden（瑞典RISE研究机构）
Enhancing Network Resilience through Machine Learning-powered Graph Combinatorial Optimization: Applications in Cyber Defense and Information Diffusion
Hybrid CNN-LSTM Framework for Intelligent Cyber Attack Detection and Prevention in U.S. Critical Digital Infrastructure: A Comparative Machine Learning Evaluation on CSE-CIC-IDS2018
Department of Computer Science, Maharishi International University（马哈拉吉国际大学计算机科学系）；Department of Information Studies, Trine University（特林大学信息学系）；Department of Business Information Systems, Central Michigan University（中央密歇根大学商业信息系统系）
