Computer Sciences Commons^™

Convolutional Neural Networks For Deflate Data Encoding Classification Of High Entropy File Fragments, Nehal Ameen

LSU New Orleans Theses and Dissertations

Data reconstruction is significantly improved in terms of speed and accuracy by reliable data encoding fragment classification. To date, work on this problem has been successful with file structures of low entropy that contain sparse data, such as large tables or logs. Classifying compressed, encrypted, and random data that exhibit high entropy is an inherently difficult problem that requires more advanced classification approaches. We explore the ability of convolutional neural networks and word embeddings to classify deflate data encoding of high entropy file fragments after establishing ground truth using controlled datasets. Our model is designed to either successfully classify file …

Sounds Of Silence: A Study Of Stability And Diversity Of Web Audio Fingerprints, Shekhar Chalise

LSU New Orleans Theses and Dissertations

Browser fingerprinting presents a grave threat to privacy as it allows user tracking even in private browsing modes. Prior measurement studies on HTML5-based fingerprinting have been limited to Canvas and WebGL but not Web Audio APIs. We aim to fill this gap by conducting the first large-scale systematic study of web audio fingerprints and studying their stability as well as diversity properties. Using MTurk and social media platforms, we collected 8 different audio fingerprints from 694 users.

Firstly, we show that the audio fingerprints are unstable unlike other fingerprinting methods with some users having as many as 20 different fingerprints. …

A Cancelable Biometric Authentication System Based On Feature-Adaptive Random Projection, Wencheng Yang, Song Wang, Muhammad Shahzad, Wei Zhou

Research outputs 2014 to 2021

Biometric template data protection is critical in preventing user privacy and identity from leakage. Random projection based cancelable biometrics is an efficient and effective technique to achieve biometric template protection. However, traditional random projection based cancelable template design suffers from the attack via record multiplicity (ARM), where an adversary obtains multiple transformed templates from different applications and the associated parameter keys so as to assemble them into a full-rank linear equation system, thereby retrieving the original feature vector. To address this issue, in this paper we propose a feature-adaptive random projection based method, in which the projection matrixes, the key …

Clickbait Detection In Youtube Videos, Ruchira Gothankar

Master's Projects

YouTube videos often include captivating descriptions and intriguing thumbnails designed to increase the number of views, and thereby increase the revenue for the person who posted the video. This creates an incentive for people to post clickbait videos, in which the content might deviate significantly from the title, description, or thumbnail. In effect, users are tricked into clicking on clickbait videos. In this research, we consider the challenging problem of detecting clickbait YouTube videos. We experiment with logistic regression, random forests, and multilayer perceptrons, based on a variety of textual features. We obtain a maximum accuracy in excess of 94%.

Malware Classification With Bert, Joel Lawrence Alvares

Master's Projects

Malware Classification is used to distinguish unique types of malware from each other.

This project aims to carry out malware classification using word embeddings which are used in Natural Language Processing (NLP) to identify and evaluate the relationship between words of a sentence. Word embeddings generated by BERT and Word2Vec for malware samples to carry out multi-class classification. BERT is a transformer based pre- trained natural language processing (NLP) model which can be used for a wide range of tasks such as question answering, paraphrase generation and next sentence prediction. However, the attention mechanism of a pre-trained BERT model can …

Fake Malware Opcodes Generation Using Hmm And Different Gan Algorithms, Harshit Trehan

Master's Projects

Malware, or malicious software, is a program that is intended to harm systems. In the past decade, the number of malware attacks have grown and, more importantly, evolved. Many researchers have successfully integrated cutting edge Machine Learning techniques to combat this ever present and growing threat to cyber and information security. One big challenge faced by many researchers is the lack of enough data to train machine learning models and specifically deep neural networks properly. Generative modelling has proven to be very efficient at generating synthesized data that can match the actual data distribution.

In this project, we aim to …

Keystroke Dynamics Based On Machine Learning, Han-Chih Chang

Master's Projects

The development of active and passive biometric authentication and identification technology plays an increasingly important role in cybersecurity. Biometrics that utilize features derived from keystroke dynamics have been studied in this context. Keystroke dynamics can be used to analyze the way that a user types by monitoring various keyboard inputs. Previous work has considered the feasibility of user authentication and classification based on keystroke features. In this research, we analyze a wide variety of machine learning and deep learning models based on keystroke-derived features, we optimize the resulting models, and we compare our results to those obtained in related research. …

Malware Analysis With Auxiliary-Classifier Gan, Rakesh Nagaraju

Master's Projects

A generative adversarial network (GAN) is a powerful machine learning concept where both a generative and discriminative model are trained simultaneously. A recent trend in malware research consists of treating executables as images and employing image-based analysis techniques. In this research, we generate fake malware images using GANs, and we also consider the effectiveness of GANs for malware classification. Specifically, we consider auxiliary classifier GAN (AC-GAN), which enables us to work with multiclass data. We find that AC-GAN generates malware images that cannot be reliably distinguished from real malware images. In addition, we find that the detection capabilities of AC-GAN …

Presentation Attack Detection In Facial Biometric Authentication, Hardik Kumar

Master's Projects

Biometric systems are referred to those structures that enable recognizing an individual, or specifically a characteristic, using biometric data and mathematical algorithms. These are known to be widely employed in various organizations and companies, mostly as authentication systems. Biometric authentic systems are usually much more secure than a classic one, however they also have some loopholes. Presentation attacks indicate those attacks which spoof the biometric systems or sensors. The presentation attacks covered in this project are: photo attacks and deepfake attacks. In the case of photo attacks, it is observed that interactive action check like Eye Blinking proves efficient in …

Machine Learning To Detect Malware Evolution, Lolitha Sresta Tupadha

Master's Projects

Malware evolves over time and anti-virus must adapt to such evolution. Hence, it is critical to detect those points in time where malware has evolved so that appro-priate countermeasures can be undertaken. In this research, we perform a variety of experiments to determine when malware evolution is likely to have occurred. All of the evolution detection techniques that we consider are based on machine learning and can be fully automated—in particular, no reverse engineering or other labor-intensive manual analysis is required. Specifically, we consider analysis based on hidden Markov models and various word embedding techniques, among other machine learning based …

Hidden Markov Model-Based Clustering For Malware Classification, Shamli Singh

Master's Projects

Automated techniques to classify malware samples into their respective families are critical in cybersecurity. Previously research applied ��-means clustering to scores generated by hidden Markov models (HMM) as a means of dealing with the malware classification problem. In this research, we follow a somewhat similar approach, but instead of using HMMs to generate scores, we directly cluster the HMMs themselves. We obtain good results on a challenging malware dataset.

Data Augmentation With Malware As Images, Aditi Walia

Master's Projects

Machine learning and deep learning techniques for malware detection and classifi- cation play an important role in the mitigation of cybersecurity threats. However, such techniques are often limited by a lack of data. Previous research has shown promising classification results by treating malware executables as images. In this research, we consider data augmentation using noise addition, geometric transforma- tions, and Auxiliary Classifier Generative Adversarial Networks (AC-GAN) for data augmentation of malware images. We train convolution neural networks (CNN) to verify that our generated images accurately model the original malware samples.

Classifying Illegal Advertisements On The Darknet Using Nlp, Karan Shashin Shah

Master's Projects

The Darknet has become a place to conduct various illegal activities like child labor, contract murder, drug selling while staying anonymous. Traditionally, international and government agencies try to control these activities, but most of those actions are manual and time-consuming. Recently, various researchers developed Machine Learning (ML) approaches trying to aid in the process of detecting illegal activities. The above problem can benefit by using different Natural Language Processing (NLP) techniques. More specifically, researchers have used various classical topic modeling techniques like bag of words, N-grams, Term Frequency, Term Frequency Inverse Document Frequency (TF-IDF) to represent features and train machine …

Fake Malware Classification With Cnn Via Image Conversion: A Game Theory Approach, Yash Sahasrabuddhe

Master's Projects

Improvements in malware detection techniques have grown significantly over the past decade. These improvements have resulted in better security for systems from various forms of malware attacks. However, it is also the reason for continuous evolution of malware which makes it harder for current security mechanisms to detect them. Hence, there is a need to understand different malwares and study classification techniques using the ever-evolving field of machine learning. The goal of this research project is to identify similarities between malware families and to improve on classification of malwares within different malware families by implementing Convolutional Neural Networks (CNNs) on …

Keystroke Dynamics For User Authentication With Fixed And Free Text, Jianwei Li

Master's Projects

YouTube videos often include captivating descriptions and intriguing thumbnails designed to increase the number of views, and thereby increase the revenue for the person who posted the video. This creates an incentive for people to post clickbait videos, in which the content might deviate significantly from the title, description, or thumbnail. In effect, users are tricked into clicking on clickbait videos. In this research, we consider the challenging problem of detecting clickbait YouTube videos. We experiment with multiple state of the art machine learning techniques and a variety of textual features.

Defending Vehicles Against Cyberthreats: Challenges And A Detection-Based Solution, Qilin Liu

Master's Projects

The lack of concern with security when vehicular network protocols were designed some thirty years ago is about to take its toll as vehicles become more connected and smart. Today as demands for more functionality and connectivity on vehicles continue to grow, a plethora of Electronic Control Units (ECUs) that are able to communicate to external networks are added to the automobile networks. The proliferation of ECU and the increasing autonomy level give drivers more control over their vehicles and make driving easier, but at the same time they expand the attack surface, bringing more vulnerabilities to vehicles that might …

Improving Additional Adversarial Robustness For Classification, Michael Guo

McKelvey School of Engineering Graduate Student Theses & Dissertations

Although neural networks have achieved remarkable success on classification, adversarial robustness is still a significant concern. There are now a series of approaches for designing adversarial examples and methods to defending against them. This paper consists of two projects. In our first work, we propose an approach by leveraging cognitive salience to enhance additional robustness on top of these methods. Specifically, for image classification, we split an image into the foreground (salient region) and background (the rest) and allow significantly larger adversarial perturbations in the background to produce stronger attacks. Furthermore, we show that adversarial training with dual-perturbation attacks yield …

If You Only Knew The Power Of The Dark Web! Finding Intellectual Freedom, Privacy, And Anonymity Online, Daniel W. Jolley

Dover Library Faculty Professional Development Activities

While the dark web attracts largely negative and sensationalistic headlines as a haven for criminality, it (and the tools used to access it) also offers knowledgeable users the ability to surf the web free of government surveillance and social media/marketing tracking and to exercise free speech in an environment of virtual anonymity. As such, the dark web supports librarians’ values regarding privacy and intellectual freedom. This presentation will give librarians a realistic look at both the positive and negative aspects of the dark web, provide them with examples of the types of users who may want to explore or make …

Moonshine: An Online Randomness Distiller For Zero-Involvement Authentication, Jack West, Kyuin Lee, Suman Banerjee, Younghyun Kim, George K. Thiruvathukal, Neil Klingensmith

Computer Science: Faculty Publications and Other Works

Context-based authentication is a method for transparently validating another device's legitimacy to join a network based on location. Devices can pair with one another by continuously harvesting environmental noise to generate a random key with no user involvement. However, there are gaps in our understanding of the theoretical limitations of environmental noise harvesting, making it difficult for researchers to build efficient algorithms for sampling environmental noise and distilling keys from that noise. This work explores the information-theoretic capacity of context-based authentication mechanisms to generate random bit strings from environmental noise sources with known properties. Using only mild assumptions about the …

Model For Quantifying The Quality Of Secure Service, Paul M. Simon, Scott R. Graham, Christopher Talbot, Micah J. Hayden

Faculty Publications

Although not common today, communications networks could adjust security postures based on changing mission security requirements, environmental conditions, or adversarial capability, through the coordinated use of multiple channels. This will require the ability to measure the security of communications networks in a meaningful way. To address this need, in this paper, we introduce the Quality of Secure Service (QoSS) model, a methodology to evaluate how well a system meets its security requirements. This construct enables a repeatable and quantifiable measure of security in a single- or multi-channel network under static configurations. In this approach, the quantification of security is based …

Heuristically Secure Threshold Lattice-Based Cryptography Schemes, James D. Dalton

Masters Theses, 2020-current

In public-key encryption, a long-term private key can be an easy target for hacking and deserves extra protection. One way to enhance its security is to share the long-term private key among multiple (say n) distributed servers; any threshold number (t, t ≤ n) of these servers are needed to collectively use the shared private key without reconstructing it. As a result, an attacker who has compromised less than t servers will still not be able to reconstruct the shared private key.

In this thesis, we studied threshold decryption schemes for lattice-based public-key en- cryption, which is one of the …

Software-Based Side Channel Attacks And The Future Of Hardened Microarchitecture, Nathaniel Hatfield

Senior Honors Theses

Side channel attack vectors found in microarchitecture of computing devices expose systems to potentially system-level breaches. This thesis consists of a comprehensive report on current exploits of this nature, describing their fundamental basis and usage, paving the way to further research into hardware mitigations that may be utilized to combat these and future vulnerabilities. It will discuss several modern software-based side channel attacks, describing the mechanisms they utilize to gain access to privileged information. Attack vectors will be exemplified, along with applicability to various architectures utilized in modern computing. Finally, discussion of how future architectural changes must successfully harden chips …

Data Forgery Detection In Automatic Generation Control: Exploration Of Automated Parameter Generation And Low-Rate Attacks, Yatish R. Dubasi

Computer Science and Computer Engineering Undergraduate Honors Theses

Automatic Generation Control (AGC) is a key control system utilized in electric power systems. AGC uses frequency and tie-line power flow measurements to determine the Area Control Error (ACE). ACE is then used by the AGC to adjust power generation and maintain an acceptable power system frequency. Attackers might inject false frequency and/or tie-line power flow measurements to mislead AGC into falsely adjusting power generation, which can harm power system operations. Various data forgery detection models are studied in this thesis. First, to make the use of predictive detection models easier for users, we propose a method for automated generation …

The Generalized Riemann Hypothesis And Applications To Primality Testing, Peter Hall

University Scholar Projects

The Riemann Hypothesis, posed in 1859 by Bernhard Riemann, is about zeros
of the Riemann zeta-function in the complex plane. The zeta-function can be repre-
sented as a sum over positive integers n of terms 1/ns when s is a complex number
with real part greater than 1. It may also be represented in this region as a prod-
uct over the primes called an Euler product. These definitions of the zeta-function
allow us to find other representations that are valid in more of the complex plane,
including a product representation over its zeros. The Riemann Hypothesis says that
all …

Sports Data Analysis – Application Of Sports Data In Athletics, Zhong Zhuang

School of Professional Studies

No abstract provided.

An Analysis Of The Applications Of Technology To Health Care Within The Caribbean And Latin America, Chineme Ezema

School of Professional Studies

This project aims to investigate and document the evolution of health technology applications and uses within the regions of Latin America and the Caribbean. Originally inspired by the Cayman Islands’ thus far successful handling of the Coronavirus pandemic, I was eager to explore how the applications of technology to the field of healthcare have existed within the region currently and over time. With this foundation, I then explored the regions’ trajectory in terms of technological growth and what the future may hold for these countries and communities.

Title Ix: Perceptions And Utilization On U.S. College Campuses, Emma Narkewicz

School of Professional Studies

The research study investigated student perceptions and utilization of Title IX services on U.S. university and college campuses, testing the hypothesis that if students hold negative perceptions of Title IX offices, then they will not report campus sexual violence they experience to Title IX offices. There are currently high rates of sexual violence on college campuses but very low rates of reporting. Current or former U.S. college students aged 18-30 (N = 47) completed a mixed methods anonymous survey composed of Likert scale and open response questions. Participants were asked about prior interactions with Title IX offices and their perceptions …

Broadband In Rhode Island, Deborah Ruggiero

School of Professional Studies

Broadband is the 21st century fiber-optic highway in our technology and information economy. The need for high-speed fiber-optic connectivity is critical for economic development, education, business, e-learning, and telehealth

Happening In Plain Sight: An Evaluation Of Sexual Harassment In Municipal Government Through A Case Study Of Newark, New Jersey, Hoween R. A. Flexer, Caitlin R. Louie

School of Professional Studies

In the city of Newark, New Jersey, Sebrevious Scott, a participant in the New Jersey Reentry program was hired as part-time office assistant in the city's re-entry office. After being transferred to the city’s Parks and Grounds Departments, she started being sexually harassed, inappropriately touched and propositioned by her supervisor, Richard Kirkland. Scott made repeated attempts to report these actions through the appropriate channels. She was met with dismissal, resistance, and later retaliation. While working in this hostile environment she was also pursuing a full-time employment opportunity with the city upon the completion of the reentry program. Unfortunately, this never …

Employee Retention Rate, Lila Sorenson

School of Professional Studies

This paper addresses the following problem regarding low employee retention rates in non-profit mental health organizations, specifically at NFI. The problem at hand is that majority of staff at NFI have an average length of stay of one year or less. The purpose of this paper is to address the current problem and hypothesize factors that could impact the low retention rates. Additionally, the purpose of the paper is to brainstorm potential solutions regarding the low retention rates and suggestions of how to implement the solutions. The documents contained in this paper include data analysis of employee average length of …