{"title":"Toward a framework for assessing the cyber-worthiness of complex mission critical systems","authors":"S. Fowler, E. Sitnikova","doi":"10.1109/MilCIS.2019.8930800","DOIUrl":"https://doi.org/10.1109/MilCIS.2019.8930800","url":null,"abstract":"Complex military systems are typically cyber-physical systems which are the targets of high level threat actors, and must be able to operate within a highly contested cyber environment. There is an emerging need to provide a strong level of assurance against these threat actors, but the process by which this assurance can be tested and evaluated is not so clear. This paper outlines an initial framework developed through research for evaluating the cyber-worthiness of complex mission critical systems using threat models developed in SysML. The framework provides a visual model of the process by which a threat actor could attack the system. It builds on existing concepts from system safety engineering and expands on how to present the risks and mitigations in an understandable manner.","PeriodicalId":210485,"journal":{"name":"2019 Military Communications and Information Systems Conference (MilCIS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127912710","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Britton, Dinesha Ranathunga, A. Coyle, Gavin Puddy
{"title":"Modelling Computational Workload in a Maritime Combat System","authors":"M. Britton, Dinesha Ranathunga, A. Coyle, Gavin Puddy","doi":"10.1109/MilCIS.2019.8930764","DOIUrl":"https://doi.org/10.1109/MilCIS.2019.8930764","url":null,"abstract":"In this paper we examine computational workload modelling in a generic maritime combat system. We show how to construct models so that executable modelling can then be used to experiment with different hardware approaches for cost, power or performance improvements. This can assist in identifying problems earlier in the design lifecycle than by using traditional design methodologies such as prototyping. We use a generic sonar suite as an exemplar, showing the considerations required in building executable models for traditional and adaptive beamforming algorithms.","PeriodicalId":210485,"journal":{"name":"2019 Military Communications and Information Systems Conference (MilCIS)","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114813371","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Performance and Integration Evaluation for Combat Systems (PIECS) Modelling and Analysis Environment: An approach to support reducing combat system design risks","authors":"Gavin Puddy","doi":"10.1109/MilCIS.2019.8930733","DOIUrl":"https://doi.org/10.1109/MilCIS.2019.8930733","url":null,"abstract":"Space., Weight and Power-Cooling (SWaP-C) are major design concerns for resource constrained platforms. With modern combat system designs increasing in complexity., approaches that provide early insight into design choice impacts becomes important and critical for design and risk mitigation efforts. In response to this and an identified modelling and analysis capability gap for combat system integration and performance evaluation., DST Group has developed a new type of measurement-based modelling and analysis environment. Built on an approach of constructing the actual system computing infrastructure and deploying models representing application behaviours., measurement-based analysis can provide for early insight in integration and performance risks associated with combat system design choices. Furthermore, this approach provides insight earlier and at a higher fidelity than traditional modelling approaches.","PeriodicalId":210485,"journal":{"name":"2019 Military Communications and Information Systems Conference (MilCIS)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133721611","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Tanvir Ishtaique ul Huque, K. Yego, Christos Sioutis, Mehdi Nobakht, E. Sitnikova, F. D. Hartog
{"title":"A system architecture for time-sensitive heterogeneous wireless distributed software-defined networks","authors":"Tanvir Ishtaique ul Huque, K. Yego, Christos Sioutis, Mehdi Nobakht, E. Sitnikova, F. D. Hartog","doi":"10.1109/MilCIS.2019.8930753","DOIUrl":"https://doi.org/10.1109/MilCIS.2019.8930753","url":null,"abstract":"Software-Defined Networking (SDN) is a relatively new technology that enables network operators to have very tight but also very flexible, policy-defined control over traffic flows in the network. Using SDN in Time-Sensitive Networking (TSN) offers network operators not only control of the network but also manageability of key network parameters such as latency, throughput, and reliability. In this paper, we discuss the state-of-the-art research related to SDN-enabled TSN networks, present system requirements for time-sensitive heterogeneous wireless distributed software-defined networks, and derive a system architecture. The proposed system architecture not only enables large distributed heterogeneous TSN networks, but also integration with other (legacy) systems, and network management by multiple operators.","PeriodicalId":210485,"journal":{"name":"2019 Military Communications and Information Systems Conference (MilCIS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128476829","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Degradation of Performance in Reinforcement Learning with State Measurement Uncertainty","authors":"Mark McKenzie, M. McDonnell","doi":"10.1109/MilCIS.2019.8930725","DOIUrl":"https://doi.org/10.1109/MilCIS.2019.8930725","url":null,"abstract":"We detail the use of open source training environments to investigate the applicability of standard reinforcement learning techniques to inherently error prone tasks expected in real world application of artificial intelligence. Numerical experiments were conducted in which the performance of both Q Learning and Policy Gradient agents' ability to obtain high reward was compared as the observation state measurement uncertainty was increased. The purpose of the research was to assess the applicability of reinforcement learning to real world applications of self-protection of military platforms, where it is expected that the observed state space is uncertain at best. We found in our experiments that Q Learning is more stable in the presence of state uncertainty than policy gradient learning.","PeriodicalId":210485,"journal":{"name":"2019 Military Communications and Information Systems Conference (MilCIS)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131401110","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Stewart, M. Britton, Dinesha Ranathunga, Gavin Puddy
{"title":"Workload Models to Evaluate Heterogeneous Compute Environments Supporting Combat Systems","authors":"M. Stewart, M. Britton, Dinesha Ranathunga, Gavin Puddy","doi":"10.1109/MilCIS.2019.8930793","DOIUrl":"https://doi.org/10.1109/MilCIS.2019.8930793","url":null,"abstract":"Model Based Systems Engineering (MBSE) is accepted as a key enabler for evaluating requirements and designs of combat systems. Systems Execution Modelling (SEM) is an MBSE approach that allows the software system to be modelled independently from the target hardware, inferring hardware characteristics by direct stimulation and measurement. SEM builds a system model out of simple workers, and this paper proposes enhancements to existing workload models to better support the evaluation of combat systems in heterogeneous compute environments comprised of CPUs and GPUs.","PeriodicalId":210485,"journal":{"name":"2019 Military Communications and Information Systems Conference (MilCIS)","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124275638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Copyright","authors":"","doi":"10.1109/milcis.2019.8930784","DOIUrl":"https://doi.org/10.1109/milcis.2019.8930784","url":null,"abstract":"","PeriodicalId":210485,"journal":{"name":"2019 Military Communications and Information Systems Conference (MilCIS)","volume":"140 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131024888","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Leveraging Deep Learning Models for Ransomware Detection in the Industrial Internet of Things Environment","authors":"M. Al-Hawawreh, E. Sitnikova","doi":"10.1109/MilCIS.2019.8930732","DOIUrl":"https://doi.org/10.1109/MilCIS.2019.8930732","url":null,"abstract":"Local Area Network (LAN) workstations that operate at the edge tier of Industrial Internet of Things systems (IIoT) and have direct or indirect interaction with critical control devices could be a key vector for advanced threats against control systems, such as a ransomware threat. This indicates that there is a necessity for monitoring these workstations to detect any malicious behavior related to ransomware, and generating an alarm to prevent the ransomware from expanding its activity to more critical system entities. The efficient detection of a ransomware attack very much relies on how accurately its activities are understood and how its traits are discovered. This can help in distinguishing ransomware from legitimate system activities. In this paper, we utilize deep learning techniques to extract the latent representation of a high dimension of collected data to identify malicious behavior accurately. Specifically, the model that we propose is based on a hybrid feature engineering technique of classical and variational auto-encoders. This hybrid technique is used to reduce the dimension of data and extract a good representation of the collected system activities. Then, the new feature vector is passed to a classifier that is built based on deep neural network and batch normalization techniques. The paper concludes with experimental results demonstrating that our model performs better in detecting ransomware compared with other existing models.","PeriodicalId":210485,"journal":{"name":"2019 Military Communications and Information Systems Conference (MilCIS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114990908","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Title Page","authors":"","doi":"10.1109/milcis.2019.8930746","DOIUrl":"https://doi.org/10.1109/milcis.2019.8930746","url":null,"abstract":"","PeriodicalId":210485,"journal":{"name":"2019 Military Communications and Information Systems Conference (MilCIS)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132947604","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}