Artificial Intelligence and Robotics Commons^™

Towards Privacy And Security Concerns Of Adversarial Examples In Deep Hashing Image Retrieval, Yanru Xiao

Computer Science Theses & Dissertations

With the explosive growth of images on the internet, image retrieval based on deep hashing attracts spotlights from both research and industry communities. Empowered by deep neural networks (DNNs), deep hashing enables fast and accurate image retrieval on large-scale data. However, inheriting from deep learning, deep hashing remains vulnerable to specifically designed input, called adversarial examples. By adding imperceptible perturbations on inputs, adversarial examples fool DNNs to make wrong decisions. The existence of adversarial examples not only raises security concerns for real-world deep learning applications, but also provides us with a technique to confront malicious applications.

In this dissertation, we …

Divide-And-Conquer Distributed Learning: Privacy-Preserving Offloading Of Neural Network Computations, Lewis C.L. Brown

Graduate Theses and Dissertations

Machine learning has become a highly utilized technology to perform decision making on high dimensional data. As dataset sizes have become increasingly large so too have the neural networks to learn the complex patterns hidden within. This expansion has continued to the degree that it may be infeasible to train a model from a singular device due to computational or memory limitations of underlying hardware. Purpose built computing clusters for training large models are commonplace while access to networks of heterogeneous devices is still typically more accessible. In addition, with the rise of 5G networks, computation at the edge becoming …

Supporting The Discovery, Reuse, And Validation Of Cybersecurity Requirements At The Early Stages Of The Software Development Lifecycle, Jessica Antonia Steinmann

Doctoral Dissertations and Master's Theses

The focus of this research is to develop an approach that enhances the elicitation and specification of reusable cybersecurity requirements. Cybersecurity has become a global concern as cyber-attacks are projected to cost damages totaling more than $10.5 trillion dollars by 2025. Cybersecurity requirements are more challenging to elicit than other requirements because they are nonfunctional requirements that requires cybersecurity expertise and knowledge of the proposed system. The goal of this research is to generate cybersecurity requirements based on knowledge acquired from requirements elicitation and analysis activities, to provide cybersecurity specifications without requiring the specialized knowledge of a cybersecurity expert, and …

Fair, Equitable, And Just: A Socio-Technical Approach To Online Safety, Daricia Wilkinson

All Dissertations

Socio-technical systems have been revolutionary in reshaping how people maintain relationships, learn about new opportunities, engage in meaningful discourse, and even express grief and frustrations. At the same time, these systems have been central in the proliferation of harmful behaviors online as internet users are confronted with serious and pervasive threats at alarming rates. Although researchers and companies have attempted to develop tools to mitigate threats, the perception of dominant (often Western) frameworks as the standard for the implementation of safety mechanisms fails to account for imbalances, inequalities, and injustices in non-Western civilizations like the Caribbean. Therefore, in this dissertation …

Are You Really Muted?: A Privacy Analysis Of Mute Buttons In Video Conferencing Apps, Yucheng Yang, Jack West, George K. Thiruvathukal, Neil Klingensmith, Kassem Fawaz

Computer Science: Faculty Publications and Other Works

In the post-pandemic era, video conferencing apps (VCAs) have converted previously private spaces — bedrooms, living rooms, and kitchens — into semi-public extensions of the office. And for the most part, users have accepted these apps in their personal space, without much thought about the permission models that govern the use of their personal data during meetings. While access to a device’s video camera is carefully controlled, little has been done to ensure the same level of privacy for accessing the microphone. In this work, we ask the question: what happens to the microphone data when a user clicks the …

Test Mimicry To Assess The Exploitability Of Library Vulnerabilities, Hong Jin Kang, Truong Giang Nguyen, Bach Le, Corina S. Pasareanu, David Lo

Research Collection School Of Computing and Information Systems

Modern software engineering projects often depend on open-source software libraries, rendering them vulnerable to potential security issues in these libraries. Developers of client projects have to stay alert of security threats in the software dependencies. While there are existing tools that allow developers to assess if a library vulnerability is reachable from a project, they face limitations. Call graphonly approaches may produce false alarms as the client project may not use the vulnerable code in a way that triggers the vulnerability, while test generation-based approaches faces difficulties in overcoming the intrinsic complexity of exploiting a vulnerability, where extensive domain knowledge …

Analysis Of Gpu Memory Vulnerabilities, Jarrett Hoover

Computer Science and Computer Engineering Undergraduate Honors Theses

Graphics processing units (GPUs) have become a widely used technology for various purposes. While their intended use is accelerating graphics rendering, their parallel computing capabilities have expanded their use into other areas. They are used in computer gaming, deep learning for artificial intelligence and mining cryptocurrencies. Their rise in popularity led to research involving several security aspects, including this paper’s focus, memory vulnerabilities. Research documented many vulnerabilities, including GPUs not implementing address space layout randomization, not zeroing out memory after deallocation, and not initializing newly allocated memory. These vulnerabilities can lead to a victim’s sensitive data being leaked to an …

Using A Bert-Based Ensemble Network For Abusive Language Detection, Noah Ballinger

Computer Science and Computer Engineering Undergraduate Honors Theses

Over the past two decades, online discussion has skyrocketed in scope and scale. However, so has the amount of toxicity and offensive posts on social media and other discussion sites. Despite this rise in prevalence, the ability to automatically moderate online discussion platforms has seen minimal development. Recently, though, as the capabilities of artificial intelligence (AI) continue to improve, the potential of AI-based detection of harmful internet content has become a real possibility. In the past couple years, there has been a surge in performance on tasks in the field of natural language processing, mainly due to the development of …

An Application Of Machine Learning To Analysis Of Packed Mac Malware, Kimo Bumanglag

Masters Theses & Doctoral Dissertations

The macOS operating system is increasingly targeted by malware. Software written for macOS, both benign and malicious, is in the Mach-O executable format. Malware authors may frustrate analysts through obfuscation methods such as packing. The field of malware research on Windows is well-established but is less so on the macOS platform. Thus far, no research has been identified that studies how machine learning can be used to detected packed Mach-O malware. This research applies supervised machine learning techniques to the classification of packed Mach-O malware. This research will answer three research questions. First, whether machine learning can classify packed Mach-O …

A Machine Learning Approach For Reconnaissance Detection To Enhance Network Security, Rachel Bakaletz

Electronic Theses and Dissertations

Before cyber-crime can happen, attackers must research the targeted organization to collect vital information about the target and pave the way for the subsequent attack phases. This cyber-attack phase is called reconnaissance or enumeration. This malicious phase allows attackers to discover information about a target to be leveraged and used in an exploit. Information such as the version of the operating system and installed applications, open ports can be detected using various tools during the reconnaissance phase. By knowing such information cyber attackers can exploit vulnerabilities that are often unique to a specific version.

In this work, we develop an …

Benchmarking Library Recognition In Tweets, Ting Zhang, Divya Prabha Chandrasekaran, Ferdian Thung, David Lo

Research Collection School Of Computing and Information Systems

Software developers often use social media (such as Twitter) to shareprogramming knowledge such as new tools, sample code snippets,and tips on programming. One of the topics they talk about is thesoftware library. The tweets may contain useful information abouta library. A good understanding of this information, e.g., on thedeveloper’s views regarding a library can be beneficial to weigh thepros and cons of using the library as well as the general sentimentstowards the library. However, it is not trivial to recognize whethera word actually refers to a library or other meanings. For example,a tweet mentioning the word “pandas" may refer to …

Deep Learning: The Many Approaches Of Intrusion Detection System Can Be Implemented And Improved Upon, Trinity Taylor

Cybersecurity Undergraduate Research Showcase

For my research topic I decided to look at Deep learning. Deep learning can be used in many ways for example in web searching. Deep learning can also can improve new businesses and products. Deep learning could lead to amazing discoveries. Deep learning is making a neural network learn something. In my research I talk about Intrusion detection system, traditional approach for intrusion detection, existing intrusion detection, machine learning and deep learning based intrusion detection system, and future work.

The Global Rise Of Online Devices, Cyber Crime And Cyber Defense: Enhancing Ethical Actions, Counter Measures, Cyber Strategy, And Approaches, Naresh Kshetri

Dissertations

The rise of online devices, online users, online shopping, online gaming, and online teaching has ultimately given rise to online attacks and online crimes. As cases of COVID-19 seem to increase day by day, so do online crimes and attacks (as many sectors and organizations went 100% online). Technological advancements and cyber warfare already generated many ethical issues, as internet users increasingly need ethical cyber defense strategies.

Individual internet users have challenges on their end; and on the other end, nation states (some secretly, some openly), are investing in robot weapons and autonomous weapons systems (AWS). New technologies have combined …

On The Influence Of Biases In Bug Localization: Evaluation And Benchmark, Ratnadira Widyasari, Stefanus Agus Haryono, Ferdian Thung, Jieke Shi, Constance Tan, Fiona Wee, Jack Phan, David Lo

Research Collection School Of Computing and Information Systems

Bug localization is the task of identifying parts of thesource code that needs to be changed to resolve a bug report.As this task is difficult, automatic bug localization tools havebeen proposed. The development and evaluation of these toolsrely on the availability of high-quality bug report datasets. In2014, Kochhar et al. identified three biases in datasets used toevaluate bug localization techniques: (1) misclassified bug report,(2) already localized bug report, and (3) incorrect ground truthfile in a bug report. They reported that already localized bugreports statistically significantly and substantially impact buglocalization results, and thus should be removed. However, theirevaluation is still limited, …

A Probabilistic Perspective Of Human-Machine Interaction, Mustafa Canan, Mustafa Demir, Samuel Kovacic

Engineering Management & Systems Engineering Faculty Publications

Human-machine interaction (HMI) has become an essential part of the daily routine in organizations. Although the machines are designed with state-of-the-art Artificial Intelligence applications, they are limited in their ability to mimic human behavior. The human-human interaction occurs between two or more humans; when a machine replaces a human, the interaction dynamics are not the same. The results indicate that a machine that interacts with a human can increase the mental uncertainty that a human experiences. Developments in decision sciences indicate that using quantum probability theory (QPT) improves the understanding of human decision-making than merely using classical probability theory (CPT). …

Understanding The Effectivity And Increased Reliance Of Credit Risk Machine Learning Models In Banking, Grishma Baruah

Cybersecurity Undergraduate Research Showcase

Credit risk analysis and making accurate investment and lending decisions has been a challenge for the financial industry for many years, as can be seen with the 2008 financial crisis. However, with the rise of machine learning models and predictive analytics, there has been a shift to increased reliance on technology for determining credit risk. This transition to machine learning comes with both advantages, such as potentially eliminating human error and assumptions from lending decisions, and disadvantages, such as time constraints, data usage inabilities, and lack of understanding nuances in machine learning models. In this paper, I look at four …

Mitigation Of Algorithmic Bias To Improve Ai Fairness, Kathy Wang

Cybersecurity Undergraduate Research Showcase

As artificial intelligence continues to evolve rapidly with emerging innovations, mass-scale digitization could be disrupted due to unfair algorithms with historically biased data. With the rising concerns of algorithmic bias, detecting biases is essential in mitigating and implementing an algorithm that promotes inclusive representation. The spread of ubiquitous artificial intelligence means that improving modeling robustness is at its most crucial point. This paper examines the omnipotence of artificial intelligence and its resulting bias, examples of AI bias in different groups, and a potential framework and mitigation strategies to improve AI fairness and remove AI bias from modeling techniques.

A Metric For Machine Learning Vulnerability To Adversarial Examples, Matt Bradley

Masters Theses & Doctoral Dissertations

Machine learning is used in myriad aspects, both in academic research and in everyday life, including safety-critical applications such as robust robotics, cybersecurity products, medial testing and diagnosis where a false positive or negative could have catastrophic results. Despite the increasing prevalence of machine learning applications and their role in critical systems we rely on daily, the security and robustness of machine learning models is still a relatively young field of research with many open questions, particularly on the defensive side of adversarial machine learning. Chief among these open questions is how best to quantify a model’s attack surface against …

Healthcare 5.0 Security Framework: Applications, Issues And Future Research Directions, Mohammad Wazid, Ashok Kumar Das, Noor Mohd, Youngho Park

VMASC Publications

Healthcare 5.0 is a system that can be deployed to provide various healthcare services. It does these services by utilising a new generation of information technologies, such as Internet of Things (IoT), Artificial Intelligence (AI), Big data analytics, blockchain and cloud computing. Due to the introduction of healthcare 5.0, the paradigm has been now changed. It is disease-centered to patient-centered care where it provides healthcare services and supports to the people. However, there are several security issues and challenges in healthcare 5.0 which may cause the leakage or alteration of sensitive healthcare data. This demands that we need a robust …

Ascp-Iomt: Ai-Enabled Lightweight Secure Communication Protocol For Internet Of Medical Things, Mohammad Wazid, Jaskaran Singh, Ashok Kumar Das, Sachin Shetty, Muhammad Khurram Khan, Joel J.P.C. Rodrigues

VMASC Publications

The Internet of Medical Things (IoMT) is a unification of smart healthcare devices, tools, and software, which connect various patients and other users to the healthcare information system through the networking technology. It further reduces unnecessary hospital visits and the burden on healthcare systems by connecting the patients to their healthcare experts (i.e., doctors) and allows secure transmission of healthcare data over an insecure channel (e.g., the Internet). Since Artificial Intelligence (AI) has a great impact on the performance and usability of an information system, it is important to include its modules in a healthcare information system, which will be …

Post-Quantum Secure Identity-Based Encryption Scheme Using Random Integer Lattices For Iot-Enabled Ai Applications, Dharminder Dharminder, Ashok Kumar Das, Sourav Saha, Basudeb Bera, Athanasios V. Vasilakos

VMASC Publications

Identity-based encryption is an important cryptographic system that is employed to ensure confidentiality of a message in communication. This article presents a provably secure identity based encryption based on post quantum security assumption. The security of the proposed encryption is based on the hard problem, namely Learning with Errors on integer lattices. This construction is anonymous and produces pseudo random ciphers. Both public-key size and ciphertext-size have been reduced in the proposed encryption as compared to those for other relevant schemes without compromising the security. Next, we incorporate the constructed identity based encryption (IBE) for Internet of Things (IoT) applications, …

Contextualized Vector Embeddings For Malware Detection, Vinay Pandya

Master's Projects

Malware classification is a technique to classify different types of malware which form an integral part of system security. The aim of this project is to use context dependant word embeddings to classify malware. Tansformers is a novel architecture which utilizes self attention to handle long range dependencies. They are particularly effective in many complex natural language processing tasks such as Masked Lan- guage Modelling(MLM) and Next Sentence Prediction(NSP). Different transfomer architectures such as BERT, DistilBert, Albert, and Roberta are used to generate context dependant word embeddings. These embeddings would help in classifying different malware samples based on their similarity …

Generative Adversarial Networks For Image-Based Malware Classification, Huy Nguyen

Master's Projects

Malware detection and analysis are important topics in cybersecurity. For efficient malware removal, determination of malware threat levels, and damage estimation, malware family classification plays a critical role. With the rise in computing power and the advent of cloud computing, deep learning models for malware analysis has gained in popularity. In this paper, we extract features from malware executable files and represent them as images using various approaches. We then focus on Generative Adversarial Networks (GAN) for multiclass classification and compare our GAN results to other popular machine learning techniques, including Support Vector Machine

(SVM), XGBoost, and Restricted Boltzmann Machines …

Faking Sensor Noise Information, Justin Chang

Master's Projects

Noise residue detection in digital images has recently been used as a method to classify images based on source camera model type. The meteoric rise in the popularity of using Neural Network models has also been used in conjunction with the concept of noise residuals to classify source camera models. However, many papers gloss over the details on the methods of obtaining noise residuals and instead rely on the self- learning aspect of deep neural networks to implicitly discover this themselves. For this project I propose a method of obtaining noise residuals (“noiseprints”) and denoising an image, as well as …

Robustness Of Image-Based Malware Analysis, Katrina Tran

Master's Projects

Being able to identify malware is important in preventing attacks. Image-based malware analysis is the study of images that are created from malware. Analyzing these images can help identify patterns in malware families. In previous work, "gist descriptor" features extracted from images have been used in malware classification problems and have shown promising results. In this research, we determine whether gist descriptors are robust with respect to malware obfuscation techniques, as compared to Convolutional Neural Networks (CNN) trained directly on malware images. Using the Python Image Library, we create images from malware executables and from malware that we obfuscate. We …

Graph Neural Networks For Malware Classification, Vrinda Malhotra

Master's Projects

Malware is a growing threat to the digital world. The first step to managing this threat is malware detection and classification. While traditional techniques rely on static or dynamic analysis of malware, the generation of these features requires expert knowledge. Function call graphs (FCGs) consist of program functions as their nodes and their interprocedural calls as their edges, providing a wealth of knowledge that can be utilized to classify malware without feature extraction that requires experts. This project treats malware classification as a graph classification problem, setting node features using the Local Degree Profile (LDP) model and using different graph …

Darknet Traffic Classification, Nhien Rust-Nguyen

Master's Projects

The anonymous nature of darknets is commonly exploited for illegal activities. Previous research has employed machine learning and deep learning techniques to automate the detection of darknet traffic to block these criminal activities. This research aims to improve darknet traffic detection by assessing Support Vector Machines (SVM), Random Forest (RF), Convolutional Neural Networks (CNN) and Auxiliary-Classifier Generative Adversarial Networks (AC-GAN) for classification of network traffic and the underlying application types. We find that our RF model outperforms the state-of-the-art machine learning techniques used by prior work with the CIC-Darknet2020 dataset. To evaluate the robustness of our RF classifier, we degrade …

Bfv-Based Homomorphic Encryption For Privacy-Preserving Cnn Models, Febrianti Wibawa, Ferhat Ozgur Catak, Salih Sarp, Murat Kuzlu

Engineering Technology Faculty Publications

Medical data is frequently quite sensitive in terms of data privacy and security. Federated learning has been used to increase the privacy and security of medical data, which is a sort of machine learning technique. The training data is disseminated across numerous machines in federated learning, and the learning process is collaborative. There are numerous privacy attacks on deep learning (DL) models that attackers can use to obtain sensitive information. As a result, the DL model should be safeguarded from adversarial attacks, particularly in medical data applications. Homomorphic encryption-based model security from the adversarial collaborator is one of the answers …

Camouflaged Poisoning Attack On Graph Neural Networks, Chao Jiang, Yi He, Richard Chapman, Hongyi Wu

Computer Science Faculty Publications

Graph neural networks (GNNs) have enabled the automation of many web applications that entail node classification on graphs, such as scam detection in social media and event prediction in service networks. Nevertheless, recent studies revealed that the GNNs are vulnerable to adversarial attacks, where feeding GNNs with poisoned data at training time can lead them to yield catastrophically devastative test accuracy. This finding heats up the frontier of attacks and defenses against GNNs. However, the prior studies mainly posit that the adversaries can enjoy free access to manipulate the original graph, while obtaining such access could be too costly in …

A Channel State Information Based Virtual Mac Spoofing Detector, Peng Jiang, Hongyi Wu, Chunsheng Xin

Electrical & Computer Engineering Faculty Publications

Physical layer security has attracted lots of attention with the expansion of wireless devices to the edge networks in recent years. Due to limited authentication mechanisms, MAC spoofing attack, also known as the identity attack, threatens wireless systems. In this paper, we study a new type of MAC spoofing attack, the virtual MAC spoofing attack, in a tight environment with strong spatial similarities, which can create multiple counterfeits entities powered by the virtualization technologies to interrupt regular services. We develop a system to effectively detect such virtual MAC spoofing attacks via the deep learning method as a countermeasure. …