Matching Items (20)
Filtering by
- All Subjects: Machine Learning
- Creators: Baral, Chitta
- Member of: Theses and Dissertations
Description
Reasoning about the activities of cyber threat actors is critical to defend against cyber
attacks. However, this task is difficult for a variety of reasons. In simple terms, it is difficult
to determine who the attacker is, what the desired goals are of the attacker, and how they will
carry out their attacks. These three questions essentially entail understanding the attacker’s
use of deception, the capabilities available, and the intent of launching the attack. These
three issues are highly inter-related. If an adversary can hide their intent, they can better
deceive a defender. If an adversary’s capabilities are not well understood, then determining
what their goals are becomes difficult as the defender is uncertain if they have the necessary
tools to accomplish them. However, the understanding of these aspects are also mutually
supportive. If we have a clear picture of capabilities, intent can better be deciphered. If we
understand intent and capabilities, a defender may be able to see through deception schemes.
In this dissertation, I present three pieces of work to tackle these questions to obtain
a better understanding of cyber threats. First, we introduce a new reasoning framework
to address deception. We evaluate the framework by building a dataset from DEFCON
capture-the-flag exercise to identify the person or group responsible for a cyber attack.
We demonstrate that the framework not only handles cases of deception but also provides
transparent decision making in identifying the threat actor. The second task uses a cognitive
learning model to determine the intent – goals of the threat actor on the target system.
The third task looks at understanding the capabilities of threat actors to target systems by
identifying at-risk systems from hacker discussions on darkweb websites. To achieve this
task we gather discussions from more than 300 darkweb websites relating to malicious
hacking.
attacks. However, this task is difficult for a variety of reasons. In simple terms, it is difficult
to determine who the attacker is, what the desired goals are of the attacker, and how they will
carry out their attacks. These three questions essentially entail understanding the attacker’s
use of deception, the capabilities available, and the intent of launching the attack. These
three issues are highly inter-related. If an adversary can hide their intent, they can better
deceive a defender. If an adversary’s capabilities are not well understood, then determining
what their goals are becomes difficult as the defender is uncertain if they have the necessary
tools to accomplish them. However, the understanding of these aspects are also mutually
supportive. If we have a clear picture of capabilities, intent can better be deciphered. If we
understand intent and capabilities, a defender may be able to see through deception schemes.
In this dissertation, I present three pieces of work to tackle these questions to obtain
a better understanding of cyber threats. First, we introduce a new reasoning framework
to address deception. We evaluate the framework by building a dataset from DEFCON
capture-the-flag exercise to identify the person or group responsible for a cyber attack.
We demonstrate that the framework not only handles cases of deception but also provides
transparent decision making in identifying the threat actor. The second task uses a cognitive
learning model to determine the intent – goals of the threat actor on the target system.
The third task looks at understanding the capabilities of threat actors to target systems by
identifying at-risk systems from hacker discussions on darkweb websites. To achieve this
task we gather discussions from more than 300 darkweb websites relating to malicious
hacking.
ContributorsNunes, Eric (Author) / Shakarian, Paulo (Thesis advisor) / Ahn, Gail-Joon (Committee member) / Baral, Chitta (Committee member) / Cooke, Nancy J. (Committee member) / Arizona State University (Publisher)
Created2018
Description
Millennials are the group of people that make up the newer generation of the world's population and they are constantly surrounded by technology, as well as known for having different values than the previous generations. Marketers have to adapt to newer ways to appeal to millennials and secure their loyalty since millennials are always on the lookout for the next best thing and will "trade up for brands that matter, but trade down when brand value is weak", it poses a challenge for the marketing departments of companies (Fromm, J. & Parks, J.). The airline industry is one of the fastest growing sectors as "the total number of people flying on U.S. airlines will increase from 745.5 million in 2014 and grow to 1.15 billion in 2034," which shows that airlines have a wider population to market to, and will need to improve their marketing strategies to differentiate from competitors (Power). The financial sector also has a difficult time reaching out to millennials because "millennials are hesitant to take financial risks," as well as downing in college debt, while not making as much money as previous generations (Fromm, J. & Parks, J.). By looking into the marketing strategies, specifically using social media platforms, of the two industries, an understanding can be gathered of what millennials are attracted to. Along with looking at the marketing strategies of financial and airline industries, I looked at the perspectives of these industries in different countries, which is important to look at because then we can see if the values of millennials vary across different cultures. Countries chosen for research to further examine their cultural differences in terms of marketing practices are the United States and England. The main form of marketing that was used for this research were social media accounts of the companies, and seeing how they used the social networking platforms to reach and engage with their consumers, especially with those of the millennial generation. The companies chosen for further research for the airline industry from England were British Airways, EasyJet, and Virgin Atlantic, while for the U.S. Delta Airlines, Inc., Southwest Airlines, and United were chosen. The companies chosen to further examine within the finance industry from England include Barclay's, HSBC, and Lloyd's Bank, while for the U.S. the banks selected were Bank of America, JPMorgan Chase, and Wells Fargo. The companies for this study were chosen because they are among the top five in their industry, as well as all companies that I have had previous interactions with. It was meant to see what the companies at the top of the industry were doing that set them apart from their competitors in terms of social media marketing content and see if there were features they lacked that could be changed or improvements they could make. A survey was also conducted to get a better idea of the attitudes and behaviors of millennials when it comes to the airline and finance industries, as well as towards social media marketing practices.
ContributorsPathak, Krisha Hemanshu (Author) / Kumar, Ajith (Thesis director) / Arora, Hina (Committee member) / W. P. Carey School of Business (Contributor) / Department of Information Systems (Contributor) / Department of Marketing (Contributor) / Hugh Downs School of Human Communication (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05
Description
Medical records are increasingly being recorded in the form of electronic health records (EHRs), with a significant amount of patient data recorded as unstructured natural language text. Consequently, being able to extract and utilize clinical data present within these records is an important step in furthering clinical care. One important aspect within these records is the presence of prescription information. Existing techniques for extracting prescription information — which includes medication names, dosages, frequencies, reasons for taking, and mode of administration — from unstructured text have focused on the application of rule- and classifier-based methods. While state-of-the-art systems can be effective in extracting many types of information, they require significant effort to develop hand-crafted rules and conduct effective feature engineering. This paper presents the use of a bidirectional LSTM with CRF tagging model initialized with precomputed word embeddings for extracting prescription information from sentences without requiring significant feature engineering. The experimental results, run on the i2b2 2009 dataset, achieve an F1 macro measure of 0.8562, and scores above 0.9449 on four of the six categories, indicating significant potential for this model.
ContributorsRawal, Samarth Chetan (Author) / Baral, Chitta (Thesis director) / Anwar, Saadat (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
The prevalence of bots, or automated accounts, on social media is a well-known problem. Some of the ways bots harm social media users include, but are not limited to, spreading misinformation, influencing topic discussions, and dispersing harmful links. Bots have affected the field of disaster relief on social media as well. These bots cause problems such as preventing rescuers from determining credible calls for help, spreading fake news and other malicious content, and generating large amounts of content which burdens rescuers attempting to provide aid in the aftermath of disasters. To address these problems, this research seeks to detect bots participating in disaster event related discussions and increase the recall, or number of bots removed from the network, of Twitter bot detection methods. The removal of these bots will also prevent human users from accidentally interacting with these bot accounts and being manipulated by them. To accomplish this goal, an existing bot detection classification algorithm known as BoostOR was employed. BoostOR is an ensemble learning algorithm originally modeled to increase bot detection recall in a dataset and it has the possibility to solve the social media bot dilemma where there may be several different types of bots in the data. BoostOR was first introduced as an adjustment to existing ensemble classifiers to increase recall. However, after testing the BoostOR algorithm on unobserved datasets, results showed that BoostOR does not perform as expected. This study attempts to improve the BoostOR algorithm by comparing it with a baseline classification algorithm, AdaBoost, and then discussing the intentional differences between the two. Additionally, this study presents the main factors which contribute to the shortcomings of the BoostOR algorithm and proposes a solution to improve it. These recommendations should ensure that the BoostOR algorithm can be applied to new and unobserved datasets in the future.
ContributorsDavis, Matthew William (Author) / Liu, Huan (Thesis director) / Nazer, Tahora H. (Committee member) / Computer Science and Engineering Program (Contributor, Contributor) / Department of Information Systems (Contributor) / Barrett, The Honors College (Contributor)
Created2018-12
Description
Abstract: The Ultimate Fighting Championship or UFC as it is commonly known, was founded in 1993 and has quickly built itself into the world's foremost authority on all things MMA (mixed martial arts) related. With pay-per-view and cable television deals in hand, the UFC has become a huge competitor in the sports market, rivaling the popularity of boxing for almost a decade. As with most other sports, the UFC has seen an influx of various analytics and data science over the past five to seven years. We see this revolution in football with the broadcast first down markers, basketball with tracking player movement, and baseball with locating pitches for strikes and balls, and now the UFC has partnered with statistics company Fightmetric, to provide in-depth statistical analysis of its fights. ESPN has their win probability metrics, and statistical predictive modeling has begun to spread throughout sports. All these stats were made to showcase the information about a fighter that one wouldn't typically know, giving insight into how the fight might go. But, can these fights be predicted? Based off of the research of prior individuals and combining the thought processes of relevant research into other sports leagues, I sought to use the arsenal of statistical analyses done by Fightmetric, along with the official UFC fighter database to answer the question of whether UFC fights could be predicted. Specifically, by using only data that would be known about a fighter prior to stepping into the cage, could I predict with any degree of certainty who was going to win the fight?
ContributorsMoorman, Taylor D. (Author) / Simon, Alan (Thesis director) / Simon, Phil (Committee member) / W.P. Carey School of Business (Contributor) / Department of Information Systems (Contributor) / Department of Management and Entrepreneurship (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
Only an Executive Summary of the project is included.
The goal of this project is to develop a deeper understanding of how machine learning pertains to the business world and how business professionals can capitalize on its capabilities. It explores the end-to-end process of integrating a machine and the tradeoffs and obstacles to consider. This topic is extremely pertinent today as the advent of big data increases and the use of machine learning and artificial intelligence is expanding across industries and functional roles. The approach I took was to expand on a project I championed as a Microsoft intern where I facilitated the integration of a forecasting machine learning model firsthand into the business. I supplement my findings from the experience with research on machine learning as a disruptive technology. This paper will not delve into the technical aspects of coding a machine model, but rather provide a holistic overview of developing the model from a business perspective. My findings show that, while the advantages of machine learning are large and widespread, a lack of visibility and transparency into the algorithms behind machine learning, the necessity for large amounts of data, and the overall complexity of creating accurate models are all tradeoffs to consider when deciding whether or not machine learning is suitable for a certain objective. The results of this paper are important in order to increase the understanding of any business professional on the capabilities and obstacles of integrating machine learning into their business operations.
The goal of this project is to develop a deeper understanding of how machine learning pertains to the business world and how business professionals can capitalize on its capabilities. It explores the end-to-end process of integrating a machine and the tradeoffs and obstacles to consider. This topic is extremely pertinent today as the advent of big data increases and the use of machine learning and artificial intelligence is expanding across industries and functional roles. The approach I took was to expand on a project I championed as a Microsoft intern where I facilitated the integration of a forecasting machine learning model firsthand into the business. I supplement my findings from the experience with research on machine learning as a disruptive technology. This paper will not delve into the technical aspects of coding a machine model, but rather provide a holistic overview of developing the model from a business perspective. My findings show that, while the advantages of machine learning are large and widespread, a lack of visibility and transparency into the algorithms behind machine learning, the necessity for large amounts of data, and the overall complexity of creating accurate models are all tradeoffs to consider when deciding whether or not machine learning is suitable for a certain objective. The results of this paper are important in order to increase the understanding of any business professional on the capabilities and obstacles of integrating machine learning into their business operations.
ContributorsVerma, Ria (Author) / Goegan, Brian (Thesis director) / Moore, James (Committee member) / Department of Information Systems (Contributor) / Department of Supply Chain Management (Contributor) / Department of Economics (Contributor) / Barrett, The Honors College (Contributor)
Created2019-05
Description
This thesis, through a thorough literature and content review, discusses the various ways that data analytics and supply chain management intersect. Both fields have been around for a while, but are incredibly aided by the information age we live in today. Today's ERP systems and supply chain software packages use advanced analytic techniques and algorithms to optimize every aspect of supply chain management. This includes aspects like inventory optimization, portfolio management, network design, production scheduling, fleet planning, supplier evaluation, and others. The benefit of these analytic techniques is a reduction in costs as well as an improvement in overall supply chain performance and efficiencies. The paper begins with a short historical context on business analytics and optimization then moves on to the impact and application of analytics in the supply chain today. Following that the implications of big data are explored, along with how a company might begin to take advantage of big data and what challenges a firm may face along the way. The current tools used by supply chain professionals are then discussed. There is then a section on the most up and coming technologies; the internet of things, blockchain technology, additive manufacturing (3D printing), and machine learning; and how those technologies may further enable the successful use of analytics to improve supply chain management. Companies that do take advantage of analytics in their supply chains are sure to maintain a competitive advantage over those firms that fail to do so.
ContributorsCotton, Ryan Aaron (Author) / Taylor, Todd (Thesis director) / Arora, Hina (Committee member) / Department of Information Systems (Contributor) / Department of Supply Chain Management (Contributor) / Barrett, The Honors College (Contributor)
Created2016-12
Description
For the past three decades, the design of an effective strategy for generating poetry that matches that of a human’s creative capabilities and complexities has been an elusive goal in artificial intelligence (AI) and natural language generation (NLG) research, and among linguistic creativity researchers in particular. This thesis presents a novel approach to fixed verse poetry generation using neural word embeddings. During the course of generation, a two layered poetry classifier is developed. The first layer uses a lexicon based method to classify poems into types based on form and structure, and the second layer uses a supervised classification method to classify poems into subtypes based on content with an accuracy of 92%. The system then uses a two-layer neural network to generate poetry based on word similarities and word movements in a 50-dimensional vector space.
The verses generated by the system are evaluated using rhyme, rhythm, syllable counts and stress patterns. These computational features of language are considered for generating haikus, limericks and iambic pentameter verses. The generated poems are evaluated using a Turing test on both experts and non-experts. The user study finds that only 38% computer generated poems were correctly identified by nonexperts while 65% of the computer generated poems were correctly identified by experts. Although the system does not pass the Turing test, the results from the Turing test suggest an improvement of over 17% when compared to previous methods which use Turing tests to evaluate poetry generators.
The verses generated by the system are evaluated using rhyme, rhythm, syllable counts and stress patterns. These computational features of language are considered for generating haikus, limericks and iambic pentameter verses. The generated poems are evaluated using a Turing test on both experts and non-experts. The user study finds that only 38% computer generated poems were correctly identified by nonexperts while 65% of the computer generated poems were correctly identified by experts. Although the system does not pass the Turing test, the results from the Turing test suggest an improvement of over 17% when compared to previous methods which use Turing tests to evaluate poetry generators.
ContributorsMagge, Arjun (Author) / Syrotiuk, Violet R. (Thesis advisor) / Baral, Chitta (Committee member) / Hogue, Cynthia (Committee member) / Bazzi, Rida (Committee member) / Arizona State University (Publisher)
Created2016
Description
Due to vast resources brought by social media services, social data mining has
received increasing attention in recent years. The availability of sheer amounts of
user-generated data presents data scientists both opportunities and challenges. Opportunities are presented with additional data sources. The abundant link information
in social networks could provide another rich source in deriving implicit information
for social data mining. However, the vast majority of existing studies overwhelmingly
focus on positive links between users while negative links are also prevailing in real-
world social networks such as distrust relations in Epinions and foe links in Slashdot.
Though recent studies show that negative links have some added value over positive
links, it is dicult to directly employ them because of its distinct characteristics from
positive interactions. Another challenge is that label information is rather limited
in social media as the labeling process requires human attention and may be very
expensive. Hence, alternative criteria are needed to guide the learning process for
many tasks such as feature selection and sentiment analysis.
To address above-mentioned issues, I study two novel problems for signed social
networks mining, (1) unsupervised feature selection in signed social networks; and
(2) unsupervised sentiment analysis with signed social networks. To tackle the first problem, I propose a novel unsupervised feature selection framework SignedFS. In
particular, I model positive and negative links simultaneously for user preference
learning, and then embed the user preference learning into feature selection. To study the second problem, I incorporate explicit sentiment signals in textual terms and
implicit sentiment signals from signed social networks into a coherent model Signed-
Senti. Empirical experiments on real-world datasets corroborate the effectiveness of
these two frameworks on the tasks of feature selection and sentiment analysis.
received increasing attention in recent years. The availability of sheer amounts of
user-generated data presents data scientists both opportunities and challenges. Opportunities are presented with additional data sources. The abundant link information
in social networks could provide another rich source in deriving implicit information
for social data mining. However, the vast majority of existing studies overwhelmingly
focus on positive links between users while negative links are also prevailing in real-
world social networks such as distrust relations in Epinions and foe links in Slashdot.
Though recent studies show that negative links have some added value over positive
links, it is dicult to directly employ them because of its distinct characteristics from
positive interactions. Another challenge is that label information is rather limited
in social media as the labeling process requires human attention and may be very
expensive. Hence, alternative criteria are needed to guide the learning process for
many tasks such as feature selection and sentiment analysis.
To address above-mentioned issues, I study two novel problems for signed social
networks mining, (1) unsupervised feature selection in signed social networks; and
(2) unsupervised sentiment analysis with signed social networks. To tackle the first problem, I propose a novel unsupervised feature selection framework SignedFS. In
particular, I model positive and negative links simultaneously for user preference
learning, and then embed the user preference learning into feature selection. To study the second problem, I incorporate explicit sentiment signals in textual terms and
implicit sentiment signals from signed social networks into a coherent model Signed-
Senti. Empirical experiments on real-world datasets corroborate the effectiveness of
these two frameworks on the tasks of feature selection and sentiment analysis.
ContributorsCheng, Kewei (Author) / Liu, Huan (Thesis advisor) / Tong, Hanghang (Committee member) / Baral, Chitta (Committee member) / Arizona State University (Publisher)
Created2017
Description
My project goes over creating a probability model to accurately predict the probability of a shot in the NHL becoming a goal. It explores different types of models to produce the most accurate model. The study explains which variables contribute most to whether a shot results in a goal or not and of those variables how teams can control them to have the most success.
ContributorsLachapelle, William (Author) / McCulloch, Robert (Thesis director) / Schneider, Laurence (Committee member) / Barrett, The Honors College (Contributor) / School of Mathematical and Statistical Sciences (Contributor) / Department of Information Systems (Contributor)
Created2023-05