Iseman: A Management And Deployment Interface For Lab-Based Activities Within Iserink, 2018 Iowa State University
Iseman: A Management And Deployment Interface For Lab-Based Activities Within Iserink, Alex Luehm
ISERink is an isolated virtual environment built within the vSphere virtualization platform in which users can safely perform various cyber security exercises without fear of damaging real-world machines. In the past it has been successfully used in cyber defense competitions to provide a network setting similar to that of the real Internet, while safely containing any rogue malicious traffic. Recently the ISERink environment has been deployed within the academic setting alongside ISELab to provide students with a safe and controlled environment in which to practice building, securing, and attacking networks in a structured lab setting in conjunction with guided lectures ...
A Simple Moving Target Defense For Power Grid Security Using Network Address Translation, 2018 Iowa State University
A Simple Moving Target Defense For Power Grid Security Using Network Address Translation, Jacob Ulrich
The Smart Grid is a Cyber Physical system which relies on the interaction between complex Information Technology (IT) networks and Operational Technology (OT) networks. In the Smart Grid, control and monitoring of physical devices is facilitated through the SCADA network. Recent attacks, such at the Ukrainian Power Grid Attack, show a rising trend of sophisticated and persistent attackers targeting the static vulnerabilities of power systems and SCADA networks .
Continuous User Authentication Via Random Forest, 2018 Iowa State University
Continuous User Authentication Via Random Forest, Ting-Wei Chang
Random forest is an important technique in modern machine learning. It was first proposed in 1995, and with the increasing of the compute power, it became a popular method in this decade. In this paper, we present the background knowledge of random forest and also have comparison with other machine learning methods. We also have some discussion of data preprocessing and feature extraction. Then we study the application of random forest to a real world problem - an authentication system which for continuous user authentication approach for web services based on the user’s behavior. The dataset we used for evaluate ...
Quantitative Fine-Grained Human Evaluation Of Machine Translation Systems: A Case Study On English To Croatian, 2018 University of Groningen
Quantitative Fine-Grained Human Evaluation Of Machine Translation Systems: A Case Study On English To Croatian, Filip Klubicka, Antonio Toral, Victor Manuel Sanchez-Cartagena
This paper presents a quantitative fine-grained manual evaluation approach to comparing the performance of different machine translation (MT) systems. We build upon the well-established Multidimensional Quality Metrics (MQM) error taxonomy and implement a novel method that assesses whether the differences in performance for MQM error types between different MT systems are statistically significant. We conduct a case study for English-to- Croatian, a language direction that involves translating into a morphologically rich language, for which we compare three MT systems belonging to different paradigms: pure phrase-based, factored phrase-based and neural. First, we design an MQM-compliant error taxonomy tailored to the relevant ...
Is It Worth It? Budget-Related Evaluation Metrics For Model Selection, 2018 Technological University Dublin
Is It Worth It? Budget-Related Evaluation Metrics For Model Selection, Filip Klubicka, Giancarlo Salton, John D. Kelleher
Projects that set out to create a linguistic resource often do so by using a machine learning model that pre-annotates or filters the content that goes through to a human annotator, before going into the final version of the resource. However, available budgets are often limited, and the amount of data that is available exceeds the amount of annotation that can be done. Thus, in order to optimize the benefit from the invested human work, we argue that the decision on which predictive model one should employ depends not only on generalized evaluation metrics, such as accuracy and F-score, but ...
Adapt At Semeval-2018 Task 9: Skip-Gram Word Embeddings For Unsupervised Hypernym Discovery In Specialised Corpora, 2018 Trinity College Dublin, Ireland
Adapt At Semeval-2018 Task 9: Skip-Gram Word Embeddings For Unsupervised Hypernym Discovery In Specialised Corpora, Alfredo Maldonado, Filip Klubicka
This paper describes a simple but competitive unsupervised system for hypernym discovery. The system uses skip-gram word embeddings with negative sampling, trained on specialised corpora. Candidate hypernyms for an input word are predicted based on cosine similar- ity scores. Two sets of word embedding mod- els were trained separately on two specialised corpora: a medical corpus and a music indus- try corpus. Our system scored highest in the medical domain among the competing unsu- pervised systems but performed poorly on the music industry domain. Our approach does not depend on any external data other than raw specialised corpora.
Examining A Hate Speech Corpus For Hate Speech Detection And Popularity Prediction, 2018 Technological University Dublin
Examining A Hate Speech Corpus For Hate Speech Detection And Popularity Prediction, Filip Klubicka, Raquel Fernandez
As research on hate speech becomes more and more relevant every day, most of it is still focused on hate speech detection. By attempting to replicate a hate speech detection experiment performed on an existing Twitter corpus annotated for hate speech, we highlight some issues that arise from doing research in the field of hate speech, which is essentially still in its infancy. We take a critical look at the training corpus in order to understand its biases, while also using it to venture beyond hate speech detection and investigate whether it can be used to shed light on other ...
Optimal Decomposition Strategy For Tree Edit Distance, 2017 The University of Western Ontario
Optimal Decomposition Strategy For Tree Edit Distance, Shaofeng Jiang
Electronic Thesis and Dissertation Repository
An ordered labeled tree is a tree where the left-to-right order among siblings is significant. Given two ordered labeled trees, the edit distance between them is the minimum cost edit operations that convert one tree to the other.
In this thesis, we present an algorithm for the tree edit distance problem by using the optimal tree decomposition strategy. By combining the vertical compression of trees with optimal decomposition we can significantly reduce the running time of the algorithm. We compare our method with other methods both theoretically and experimentally. The test results show that our strategies on compressed trees are ...
Demand Side Management In Smart Grid Using Big Data Analytics, 2017 Utah State University
Demand Side Management In Smart Grid Using Big Data Analytics, Sidhant Chatterjee
All Graduate Plan B and other Reports
Smart Grids are the next generation electrical grid system that utilizes smart meter-ing devices and sensors to manage the grid operations. Grid management includes the prediction of load and and classiﬁcation of the load patterns and consumer usage behav-iors. These predictions can be performed using machine learning methods which are often supervised. Supervised machine learning signiﬁes that the algorithm trains the model to eﬃciently predict decisions based on the previously available data.
Smart grids are employed with numerous smart meters that send user statistics to a central server. The data can be accumulated and processed using data mining and machine ...
A Data Hiding Scheme Based On Chaotic Map And Pixel Pairs, 2017 Firat University
A Data Hiding Scheme Based On Chaotic Map And Pixel Pairs, Sengul Dogan Sd
Journal of Digital Forensics, Security and Law
Information security is one of the most common areas of study today. In the literature, there are many algorithms developed in the information security. The Least Significant Bit (LSB) method is the most known of these algorithms. LSB method is easy to apply however it is not effective on providing data privacy and robustness. In spite of all its disadvantages, LSB is the most frequently used algorithm in literature due to providing high visual quality. In this study, an effective data hiding scheme alternative to LSB, 2LSBs, 3LSBs and 4LSBs algorithms (known as xLSBs), is proposed. In this method, random ...
Streaming Mysql Database Activity To Aws Kinesis, 2017 California Polytechnic State University, San Luis Obispo
Streaming Mysql Database Activity To Aws Kinesis, Chris I. Voncina
No abstract provided.
Real Time And High Fidelity Quadcopter Tracking System, 2017 California Polytechnic State University, San Luis Obispo
Real Time And High Fidelity Quadcopter Tracking System, Tyler Mckay Hall
This project was conceived as a desired to have an affordable, flexible and physically compact tracking system for high accuracy spatial and orientation tracking. Specifically, this implementation is focused on providing a low cost motion capture system for future research. It is a tool to enable the further creation of systems that would require the use of accurate placement of landing pads, payload acquires and delivery. This system will provide the quadcopter platform a coordinate system that can be used in addition to GPS.
Field research with quadcopter manufacturers, photographers, agriculture and research organizations were contact and interviewed for information ...
Cloudskulk: Design Of A Nested Virtual Machine Based Rootkit-In-The-Middle Attack, 2017 Boise State University
Cloudskulk: Design Of A Nested Virtual Machine Based Rootkit-In-The-Middle Attack, Joseph Anthony Connelly
Boise State University Theses and Dissertations
Virtualized cloud computing services are a crucial facet in the software industry today, with clear evidence of its usage quickly accelerating. Market research forecasts an increase in cloud workloads by more than triple, 3.3-fold, from 2014 to 2019 . Integrating system security is then an intrinsic concern of cloud platform system administrators that with the growth of cloud usage, is becoming increasingly relevant. People working in the cloud demand security more than ever. In this paper, we take an offensive, malicious approach at targeting such cloud environments as we hope both cloud platform system administrators and software developers of ...
Pubwc Bathroom Review App, 2017 California Polytechnic State University, San Luis Obispo
Pubwc Bathroom Review App, Clay Jacobs
Computer Science and Software Engineering
For my senior project, I developed an iOS application to allow
users to find, rate, and review nearby public restrooms. The app takes
advantage of crowdsourced data to collect bathroom and review
information. I also created a REST API to interface with the backend
database that could be used to port the application to other platforms.
Applied Deep Learning: Automated Segmentation Of White Matter Hyperintensities (Wmh) On Brain Mr Images, 2017 University of North Florida
Applied Deep Learning: Automated Segmentation Of White Matter Hyperintensities (Wmh) On Brain Mr Images, Matt Berseth
DHI Digital Projects Showcase
Small vessel disease plays a crucial role in stroke, dementia, and ageing. White matter hyperintensities (WMH) of vascular origin are one of the main consequences of small vessel disease and well visible on brain MR images. Quantification of WMH volume, location, and shape is of key importance in clinical research studies and likely to find its way into clinical practice; supporting diagnosis, prognosis, and monitoring of treatment for dementia and other neurodegenerative diseases. It has been noted that visual rating of WMH has important limitations and hence a more detailed segmentation of WMH is preferred. Various automated WMH segmentation techniques ...
How The National Library Of Medicine Can Add Evidence To Your Mhealth App, 2017 University of Massachusetts Medical School
How The National Library Of Medicine Can Add Evidence To Your Mhealth App, Susan Halpin, Sherry Pagoto
National Network of Libraries of Medicine New England Region (NNLM NER) Repository
Numerous systematic reviews of health-related mobile apps reveal they lack evidence based content. A major challenge to including evidence based content in apps is how to efficiently find accurate, credible, and vetted content. The National Library of Medicine houses the largest biomedical library in the world and provides numerous expert-developed online resources on disease and health education. In this webinar, Susan Halpin of the National Library of Medicine will introduce attendees to those resources, give examples of how they can and have been used in mobile apps, and discuss funding opportunities offered by the NLM.
2fly With Rpi - Evaluating The Raspberry Pi For Glass Cockpit Applications, 2017 Southern Illinois University Carbondale
2fly With Rpi - Evaluating The Raspberry Pi For Glass Cockpit Applications, Donald R. Morris
ASA Multidisciplinary Research Symposium
Evaluating the capabilities of Raspberry Pi computers to be used in embedded glass cockpit applications for experimental aircraft. This includes details of what is required for these applications as well as how well the Raspberry Pi 3B can perform in this role.
Benchmarking Estonia's Cyber Security: An On-Ramping Methodology For Rapid Adoption And Implementation, 2017 United States Military Academy
Benchmarking Estonia's Cyber Security: An On-Ramping Methodology For Rapid Adoption And Implementation, Ernest Wong, Nan Porter, Mckinnon Hokanson, Bing Bing Xie
In April of 2007, Estonia fell victim to a series of distributed denial of service (DDoS) attacks that crippled its government websites, email servers, media outlets, and banking system for nearly a month. Due to the devastating effects of these cyber attacks, Estonia took great efforts to strengthen its cyber security protocols. This research analyzes the reforms that Estonia has implemented in its domestic and foreign policies and attempts to determine if any of it systemic improvements can help to also bolster cyber security in the United States (US). The findings from this research are that Estonia’s policy reforms ...
Simple Implementation Of An Elgamal Digital Signature And A Brute Force Attack On It, 2017 Embry-Riddle Aeronautical University
Simple Implementation Of An Elgamal Digital Signature And A Brute Force Attack On It, Valeriia Laryoshyna
This study is an attempt to show a basic mathematical usage of the concepts behind digital signatures and to provide a simple approach and understanding to cracking basic digital signatures. The approach takes on simple C programming of the ElGamal digital signature to identify some limits that can be encountered and provide considerations for making more complex code. Additionally, there is a literature review of the ElGamal digital signature and the brute force attack.
The research component of this project provides a list of possible ways to crack the basic implementations and classifies the different approaches that could be taken ...
Natural Language Processing Based Generator Of Testing Instruments, 2017 California State University, San Bernardino
Natural Language Processing Based Generator Of Testing Instruments, Qianqian Wang
Electronic Theses, Projects, and Dissertations
Natural Language Processing (NLP) is the field of study that focuses on the interactions between human language and computers. By “natural language” we mean a language that is used for everyday communication by humans. Different from programming languages, natural languages are hard to be defined with accurate rules. NLP is developing rapidly and it has been widely used in different industries. Technologies based on NLP are becoming increasingly widespread, for example, Siri or Alexa are intelligent personal assistants using NLP build in an algorithm to communicate with people. “Natural Language Processing Based Generator of Testing Instruments” is a stand-alone program ...