Defense Notices
All students and faculty are welcome to attend the final defense of EECS graduate students completing their M.S. or Ph.D. degrees. Defense notices for M.S./Ph.D. presentations for this year and several previous years are listed below in reverse chronological order.
Students who are nearing the completion of their M.S./Ph.D. research should schedule their final defenses through the EECS graduate office at least THREE WEEKS PRIOR to their presentation date so that there is time to complete the degree requirements check, and post the presentation announcement online.
Upcoming Defense Notices
Mahmudul Hasan
Assertion-Based Security Assessment of Hardware IP Protection MethodsWhen & Where:
Eaton Hall, Room 2001B
Committee Members:
Tamzidul Hoque, ChairEsam El-Araby
Sumaiya Shomaji
Abstract
Combinational and sequential locking methods are promising solutions for protecting hardware intellectual property (IP) from piracy, reverse engineering, and malicious modifications by locking the functionality of the IP based on a secret key. To improve their security, researchers are developing attack methods to extract the secret key.
While the attacks on combinational locking are mostly inapplicable for sequential designs without access to the scan chain, the limited applicable attacks are generally evaluated against the basic random insertion of key gates. On the other hand, attacks on sequential locking techniques suffer from scalability issues and evaluation of improperly locked designs. Finally, while most attacks provide an approximately correct key, they do not indicate which specific key bits are undetermined. This thesis proposes an oracle-guided attack that applies to both combinational and sequential locking without scan chain access. The attack applies light-weight design modifications that represent the oracle using a finite state machine and applies an assertion-based query of the unlocking key. We have analyzed the effectiveness of our attack against 46 sequential designs locked with various classes of combinational locking including random, strong, logic cone-based, and anti-SAT based. We further evaluated against a sequential locking technique using 46 designs with various key sequence lengths and widths. Finally, we expand our framework to identify undetermined key bits, enabling complementary attacks on the smaller remaining key space.
Masoud Ghazikor
Distributed Optimization and Control Algorithms for UAV Networks in Unlicensed Spectrum BandsWhen & Where:
Nichols Hall, Room 246 (Executive Conference Room)
Committee Members:
Morteza Hashemi, ChairVictor Frost
Prasad Kulkarni
Abstract
UAVs have emerged as a transformative technology for various applications, including emergency services, delivery, and video streaming. Among these, video streaming services in areas with limited physical infrastructure, such as disaster-affected areas, play a crucial role in public safety. UAVs can be rapidly deployed in search and rescue operations to efficiently cover large areas and provide live video feeds, enabling quick decision-making and resource allocation strategies. However, ensuring reliable and robust UAV communication in such scenarios is challenging, particularly in unlicensed spectrum bands, where interference from other nodes is a significant concern. To address this issue, developing a distributed transmission control and video streaming is essential to maintaining a high quality of service, especially for UAV networks that rely on delay-sensitive data.
In this MSc thesis, we study the problem of distributed transmission control and video streaming optimization for UAVs operating in unlicensed spectrum bands. We develop a cross-layer framework that jointly considers three inter-dependent factors: (i) in-band interference introduced by ground-aerial nodes at the physical layer, (ii) limited-size queues with delay-constrained packet arrival at the MAC layer, and (iii) video encoding rate at the application layer. This framework is designed to optimize the average throughput and PSNR by adjusting fading thresholds and video encoding rates for an integrated aerial-ground network in unlicensed spectrum bands. Using consensus-based distributed algorithm and coordinate descent optimization, we develop two algorithms: (i) Distributed Transmission Control (DTC) that dynamically adjusts fading thresholds to maximize the average throughput by mitigating trade-offs between low-SINR transmission errors and queue packet losses, and (ii) Joint Distributed Video Transmission and Encoder Control (JDVT-EC) that optimally balances packet loss probabilities and video distortions by jointly adjusting fading thresholds and video encoding rates. Through extensive numerical analysis, we demonstrate the efficacy of the proposed algorithms under various scenarios.
Ganesh Nurukurti
Customer Behavior Analytics and Recommendation System for E-CommerceWhen & Where:
Eaton Hall, Room 2001B
Committee Members:
David Johnson, ChairPrasad Kulkarni
Han Wang
Abstract
In the era of digital commerce, personalized recommendations are pivotal for enhancing user experience and boosting engagement. This project presents a comprehensive recommendation system integrated into an e-commerce web application, designed using Flask and powered by collaborative filtering via Singular Value Decomposition (SVD). The system intelligently predicts and personalizes product suggestions for users based on implicit feedback such as purchases, cart additions, and search behavior.
The foundation of the recommendation engine is built on user-item interaction data, derived from the Brazilian e-commerce Olist dataset. Ratings are simulated using weighted scores for purchases and cart additions, reflecting varying degrees of user intent. These interactions are transformed into a user-product matrix and decomposed using SVD, yielding latent user and product features. The model leverages these latent factors to predict user interest in unseen products, enabling precise and scalable recommendation generation.
To further enhance personalization, the system incorporates real-time user activity. Recent search history is stored in an SQLite database and used to prioritize recommendations that align with the user’s current interests. A diversity constraint is also applied to avoid redundancy, limiting the number of recommended products per category.
The web application supports robust user authentication, product exploration by category, cart management, and checkout simulations. It features a visually driven interface with dynamic visualizations for product insights and user interactions. The home page adapts to individual preferences, showing tailored product recommendations and enabling users to explore categories and details.
In summary, this project demonstrates the practical implementation of a hybrid recommendation strategy combining matrix factorization with contextual user behavior. It showcases the importance of latent factor modeling, data preprocessing, and user-centric design in delivering an intelligent retail experience.
Srijanya Chetikaneni
Plant Disease Prediction Using Transfer LearningWhen & Where:
Eaton Hall, Room 2001B
Committee Members:
David Johnson, ChairPrasad Kulkarni
Han Wang
Abstract
Timely detection of plant diseases is critical to safeguarding crop yields and ensuring global food security. This project presents a deep learning-based image classification system to identify plant diseases using the publicly available PlantVillage dataset. The core objective was to evaluate and compare the performance of a custom-built Convolutional Neural Network (CNN) with two widely used transfer learning models—EfficientNetB0 and MobileNetV3Small.
All models were trained on augmented image data resized to 224×224 pixels, with preprocessing tailored to each architecture. The custom CNN used simple normalization, whereas EfficientNetB0 and MobileNetV3Small utilized their respective pre-processing methods to standardize the pretrained ImageNet domain inputs. To improve robustness, the training pipeline included data augmentation, class weighting, and early stopping.
Training was conducted using the Adam optimizer and categorical cross-entropy loss over 30 epochs, with performance assessed using accuracy, loss, and training time metrics. The results revealed that transfer learning models significantly outperformed the custom CNN. EfficientNetB0 achieved the highest accuracy, making it ideal for high-precision applications, while MobileNetV3Small offered a favorable balance between speed and accuracy, making it suitable for lightweight, real-time inference on edge devices.
This study validates the effectiveness of transfer learning for plant disease detection tasks and emphasizes the importance of model-specific preprocessing and training strategies. It provides a foundation for deploying intelligent plant health monitoring systems in practical agricultural environments.
Ahmet Soyyigit
Anytime Computing Techniques for LiDAR-based Perception In Cyber-Physical SystemsWhen & Where:
Nichols Hall, Room 250 (Gemini Room)
Committee Members:
Heechul Yun, ChairMichael Branicky
Prasad Kulkarni
Hongyang Sun
Shawn Keshmiri
Abstract
The pursuit of autonomy in cyber-physical systems (CPS) presents a challenging task of real-time interaction with the physical world, prompting extensive research in this domain. Recent advances in artificial intelligence (AI), particularly the introduction of deep neural networks (DNN), have significantly improved the autonomy of CPS, notably by boosting perception capabilities.
CPS perception aims to discern, classify, and track objects of interest in the operational environment, a task that is considerably challenging for computers in a three-dimensional (3D) space. For this task, the use of LiDAR sensors and processing their readings with DNNs has become popular because of their excellent performance However, in CPS such as self-driving cars and drones, object detection must be not only accurate but also timely, posing a challenge due to the high computational demand of LiDAR object detection DNNs. Satisfying this demand is particularly challenging for on-board computational platforms due to size, weight, and power constraints. Therefore, a trade-off between accuracy and latency must be made to ensure that both requirements are satisfied. Importantly, the required trade-off is operational environment dependent and should be weighted more on accuracy or latency dynamically at runtime. However, LiDAR object detection DNNs cannot dynamically reduce their execution time by compromising accuracy (i.e. anytime computing). Prior research aimed at anytime computing for object detection DNNs using camera images is not applicable to LiDAR-based detection due to architectural differences. This thesis addresses these challenges by proposing three novel techniques: Anytime-LiDAR, which enables early termination with reasonable accuracy; VALO (Versatile Anytime LiDAR Object Detection), which implements deadline-aware input data scheduling; and MURAL (Multi-Resolution Anytime Framework for LiDAR Object Detection), which introduces dynamic resolution scaling. Together, these innovations enable LiDAR-based object detection DNNs to make effective trade-offs between latency and accuracy under varying operational conditions, advancing the practical deployment of LiDAR object detection DNNs.
Rahul Purswani
Finetuning Llama on custom data for QA tasksWhen & Where:
Eaton Hall, Room 2001B
Committee Members:
David Johnson, ChairDrew Davidson
Prasad Kulkarni
Abstract
Fine-tuning large language models (LLMs) for domain-specific use cases, such as question answering, offers valuable insights into how their performance can be tailored to specialized information needs. In this project, we focused on the University of Kansas (KU) as our target domain. We began by scraping structured and unstructured content from official KU webpages, covering a wide array of student-facing topics including campus resources, academic policies, and support services. From this content, we generated a diverse set of question-answer pairs to form a high-quality training dataset. LLaMA 3.2 was then fine-tuned on this dataset to improve its ability to answer KU-specific queries with greater relevance and accuracy. Our evaluation revealed mixed results—while the fine-tuned model outperformed the base model on most domain-specific questions, the original model still had an edge in handling ambiguous or out-of-scope prompts. These findings highlight the strengths and limitations of domain-specific fine-tuning, and provide practical takeaways for customizing LLMs for real-world QA applications.
Rithvij Pasupuleti
A Machine Learning Framework for Identifying Bioinformatics Tools and Database Names in Scientific LiteratureWhen & Where:
LEEP2, Room 2133
Committee Members:
Cuncong Zhong, ChairDongjie Wang
Han Wang
Zijun Yao
Abstract
The absence of a single, comprehensive database or repository cataloging all bioinformatics databases and software creates a significant barrier for researchers aiming to construct computational workflows. These workflows, which often integrate 10–15 specialized tools for tasks such as sequence alignment, variant calling, functional annotation, and data visualization, require researchers to explore diverse scientific literature to identify relevant resources. This process demands substantial expertise to evaluate the suitability of each tool for specific biological analyses, alongside considerable time to understand their applicability, compatibility, and implementation within a cohesive pipeline. The lack of a central, updated source leads to inefficiencies and the risk of using outdated tools, which can affect research quality and reproducibility. Consequently, there is a critical need for an automated, accurate tool to identify bioinformatics databases and software mentions directly from scientific texts, streamlining workflow development and enhancing research productivity.
The bioNerDS system, a prior effort to address this challenge, uses a rule-based named entity recognition (NER) approach, achieving an F1 score of 63% on an evaluation set of 25 articles from BMC Bioinformatics and PLoS Computational Biology. By integrating the same set of features such as context patterns, word characteristics and dictionary matches into a machine learning model, we developed an approach using an XGBoost classifier. This model, carefully tuned to address the extreme class imbalance inherent in NER tasks through synthetic oversampling and refined via systematic hyperparameter optimization to balance precision and recall, excels at capturing complex linguistic patterns and non-linear relationships, ensuring robust generalization. It achieves an F1 score of 82% on the same evaluation set, significantly surpassing the baseline. By combining rule-based precision with machine learning adaptability, this approach enhances accuracy, reduces ambiguities, and provides a robust tool for large-scale bioinformatics resource identification, facilitating efficient workflow construction. Furthermore, this methodology holds potential for extension to other technological domains, enabling similar resource identification in fields like data science, artificial intelligence, or computational engineering.
Vishnu Chowdary Madhavarapu
Automated Weather Classification Using Transfer LearningWhen & Where:
Nichols Hall, Room 246 (Executive Conference Room)
Committee Members:
David Johnson, ChairPrasad Kulkarni
Dongjie Wang
Abstract
This project presents an automated weather classification system utilizing transfer learning with pre-trained convolutional neural networks (CNNs) such as VGG19, InceptionV3, and ResNet50. Designed to classify weather conditions—sunny, cloudy, rainy, and sunrise—from images, the system addresses the challenge of limited labeled data by applying data augmentation techniques like zoom, shear, and flip, expanding the dataset images. By fine-tuning the final layers of pre-trained models, the solution achieves high accuracy while significantly reducing training time. VGG19 was selected as the baseline model for its simplicity, strong feature extraction capabilities, and widespread applicability in transfer learning scenarios. The system was trained using the Adam optimizer and evaluated on key performance metrics including accuracy, precision, recall, and F1 score. To enhance user accessibility, a Flask-based web interface was developed, allowing real-time image uploads and instant weather classification. The results demonstrate that transfer learning, combined with robust data preprocessing and fine-tuning, can produce a lightweight and accurate weather classification tool. This project contributes toward scalable, real-time weather recognition systems that can integrate into IoT applications, smart agriculture, and environmental monitoring.
RokunuzJahan Rudro
Using Machine Learning to Classify Driver Behavior from Psychological Features: An Exploratory StudyWhen & Where:
Eaton Hall, Room 1A
Committee Members:
Sumaiya Shomaji, ChairDavid Johnson
Zijun Yao
Alexandra Kondyli
Abstract
Driver inattention and human error are the primary causes of traffic crashes. However, little is known about the relationship between driver aggressiveness and safety. Although several studies that group drivers into different classes based on their driving performance have been conducted, little has been done to explore how behavioral traits are linked to driver behavior. The study aims to link different driver profiles, assessed through psychological evaluations, with their likelihood of engaging in risky driving behaviors, as measured in a driving simulation experiment. By incorporating psychological factors into machine learning algorithms, our models were able to successfully relate self-reported decision-making and personality characteristics with actual driving actions. Our results hold promise toward refining existing models of driver behavior by understanding the psychological and behavioral characteristics that influence the risk of crashes.
Md Mashfiq Rizvee
Energy Optimization in Multitask Neural Networks through Layer SharingWhen & Where:
Eaton Hall, Room 2001B
Committee Members:
Sumaiya Shomaji, ChairTamzidul Hoque
Han Wang
Abstract
Artificial Intelligence (AI) is being widely used in diverse domains such as industrial automation, traffic control, precision agriculture, and smart cities for major heavy lifting in terms of data analysis and decision making. However, the AI life- cycle is a major source of greenhouse gas (GHG) emission leading to devastating environmental impact. This is due to expensive neural architecture searches, training of countless number of models per day across the world, in-field AI processing of data in billions of edge devices, and advanced security measures across the AI life cycle. Modern applications often involve multitasking, which involves performing a variety of analyzes on the same dataset. These tasks are usually executed on resource-limited edge devices, necessitating AI models that exhibit efficiency across various measures such as power consumption, frame rate, and model size. To address these challenges, we introduce a novel neural network architecture model that incorporates a layer sharing principle to optimize the power usage. We propose a novel neural architecture, Layer Shared Neural Networks that merges multiple similar AI/NN tasks together (with shared layers) towards creating a single AI/NN model with reduced energy requirements and carbon footprint. The experimental findings reveal competitive accuracy and reduced power consumption. The layer shared model significantly reduces power consumption by 50% during training and 59.10% during inference causing as much as an 84.64% and 87.10% decrease in CO2 emissions respectively.
Fairuz Shadmani Shishir
Parameter-Efficient Computational Drug Discovery using Deep LearningWhen & Where:
Eaton Hall, Room 2001B
Committee Members:
Sumaiya Shomaji, ChairTamzidul Hoque
Hongyang Sun
Abstract
The accurate prediction of small molecule binding affinity and toxicity remains a central challenge in drug discovery, with significant implications for reducing development costs, improving candidate prioritization, and enhancing safety profiles. Traditional computational approaches, such as molecular docking and quantitative structure-activity relationship (QSAR) models, often rely on handcrafted features and require extensive domain knowledge, which can limit scalability and generalization to novel chemical scaffolds. Recent advances in language models (LMs), particularly those adapted to chemical representations such as SMILES (Simplified Molecular Input Line Entry System), have opened new ways for learning data-driven molecular representations that capture complex structural and functional properties. However, achieving both high binding affinity and low toxicity through a resource-efficient computational pipeline is inherently difficult due to the multi-objective nature of the task. This study presents a novel dual-paradigm approach to critical challenges in drug discovery: predicting small molecules with high binding affinity and low cardiotoxicity profiles. For binding affinity prediction, we implement a specialized graph neural network (GNN) architecture that operates directly on molecular structures represented as graphs, where atoms serve as nodes and bonds as edges. This topology-aware approach enables the model to capture complex spatial arrangements and electronic interactions critical for protein-ligand binding. For toxicity prediction, we leverage chemical language models (CLMs) fine-tuned with Low-Rank Adaptation (LoRA), allowing efficient adaptation of large pre-trained models to specialized toxicological endpoints while maintaining the generalized chemical knowledge embedded in the base model. Our hybrid methodology demonstrates significant improvements over existing computational approaches, with the GNN component achieving an average area under the ROC curve (AUROC) of 0.92 on three protein targets and the LoRA-adapted CLM reaching (AUROC) of 0.90 with 60% reduction in parameter usage in predicting cardiotoxicity. This work establishes a powerful computational framework that accelerates drug discovery by enabling both higher binding affinity and low toxicity compounds with optimized efficacy and safety profiles.
Soma Pal
Truths about compiler optimization for state-of-the-art (SOTA) C/C++ compilersWhen & Where:
Eaton Hall, Room 2001B
Committee Members:
Prasad Kulkarni, ChairEsam El-Araby
Drew Davidson
Tamzidul Hoque
Jiang Yunfeng
Abstract
Compiler optimizations are critical for performance and have been extensively studied, especially for C/C++ language compilers. Our overall goal in this thesis is to investigate and compare the properties and behavior of optimization passes across multiple contemporary, state-of-the-art (SOTA) C/C++ compilers to understand if they adopt similar optimization implementation and orchestration strategies. Given the maturity of pre-existing knowledge in the field, it seems conceivable that different compiler teams will adopt consistent optimization passes, pipeline and application techniques. However, our preliminary results indicate that such expectation may be misguided. If so, then we will attempt to understand the differences, and study and quantify their impact on the performance of generated code.
In our first work, we study and compare the behavior of profile-guided optimizations (PGO) in two popular SOTA C/C++ compilers, GCC and Clang. This study reveals many interesting, and several counter-intuitive, properties about PGOs in C/C++ compilers. The behavior and benefits of PGOs also vary significantly across our selected compilers. We present our observations, along with plans to further explore these inconsistencies in this report. Likewise, we have also measured noticeable differences in the performance delivered by optimizations across our compilers. We propose to explore and understand these differences in this work. We present further details regarding our proposed directions and planned experiments in this report. We hope that this work will show and suggest opportunities for compilers to learn from each other and motivate researchers to find mechanisms to combine the benefits of multiple compilers to deliver higher overall program performance.
Nyamtulla Shaik
AI Vision to Care: A QuadView of Deep Learning for Detecting Harmful Stimming in AutismWhen & Where:
Eaton Hall, Room 2001B
Committee Members:
Sumaiya Shomaji, ChairBo Luo
Dongjie Wang
Abstract
Stimming refers to repetitive actions or behaviors used to regulate sensory input or express feelings. Children with developmental disorders like autism (ASD) frequently perform stimming. This includes arm flapping, head banging, finger flicking, spinning, etc. This is exhibited by 80-90% of children with Autism, which is seen in 1 among 36 children in the US. Head banging is one of these self-stimulatory habits that can be harmful. If these behaviors are automatically identified and notified using live video monitoring, parents and other caregivers can better watch over and assist children with ASD.
Classifying these actions is important to recognize harmful stimming, so this study focuses on developing a deep learning-based approach for stimming action recognition. We implemented and evaluated four models leveraging three deep learning architectures based on Convolutional Neural Networks (CNNs), Autoencoders, and Vision Transformers. For the first time in this area, we use skeletal joints extracted from video sequences. Previous works relied solely on raw RGB videos, vulnerable to lighting and environmental changes. This research explores Deep Learning based skeletal action recognition and data processing techniques for a small unstructured dataset that consists of 89 home recorded videos collected from publicly available sources like YouTube. Our robust data cleaning and pre-processing techniques helped the integration of skeletal data in stimming action recognition, which performed better than state-of-the-art with a classification accuracy of up to 87%
In addition to using traditional deep learning models like CNNs for action recognition, this study is among the first to apply data-hungry models like Vision Transformers (ViTs) and Autoencoders for stimming action recognition on the dataset. The results prove that using skeletal data reduces the processing time and significantly improves action recognition, promising a real-time approach for video monitoring applications. This research advances the development of automated systems that can assist caregivers in more efficiently tracking stimming activities.
Alexander Rodolfo Lara
Creating a Faradaic Efficiency Graph Dataset Using Machine LearningWhen & Where:
Eaton Hall, Room 2001B
Committee Members:
Zijun Yao, ChairSumaiya Shomaji
Kevin Leonard
Abstract
Just as the internet-of-things leverages machine learning over a vast amount of data produced by an innumerable number of sensors, the Internet of Catalysis program uses similar strategies with catalysis research. One application of the Internet of Catalysis strategy is treating research papers as datapoints, rich with text, figures, and tables. Prior research within the program focused on machine learning models applied strictly over text.
This project is the first step of the program in creating a machine learning model from the images of catalysis research papers. Specifically, this project creates a dataset of faradaic efficiency graphs using transfer learning from pretrained models. The project utilizes FasterRCNN_ResNet50_FPN, LayoutLMv3SequenceClassification, and computer vision techniques to recognize figures, extract all graphs, then classify the faradaic efficiency graphs.
Downstream of this project, researchers will create a graph reading model to integrate with large language models. This could potentially lead to a multimodal model capable of fully learning from images, tables, and texts of catalysis research papers. Such a model could then guide experimentation on reaction conditions, catalysts, and production.
Amin Shojaei
Scalable and Cooperative Multi-Agent Reinforcement Learning for Networked Cyber-Physical Systems: Applications in Smart GridsWhen & Where:
Nichols Hall, Room 246 (Executive Conference Room)
Committee Members:
Morteza Hashemi, ChairAlex Bardas
Prasad Kulkarni
Taejoon Kim
Shawn Keshmiri
Abstract
Significant advances in information and networking technologies have transformed Cyber-Physical Systems (CPS) into networked cyber-physical systems (NCPS). A noteworthy example of such systems is smart grid networks, which include distributed energy resources (DERs), renewable generation, and the widespread adoption of Electric Vehicles (EVs). Such complex NCPS require intelligent and autonomous control solutions. For example, the increasing number of EVs introduces significant sources of demand and user behavior uncertainty that can jeopardize grid stability during peak hours. Traditional model-based demand-supply controls fail to accurately model and capture the complex nature of smart grid systems in the presence of different uncertainties and as the system size grows. To address these challenges, data-driven approaches have emerged as an effective solution for informed decision-making, predictive modeling, and adaptive control to enhance the resiliency of NCPS in uncertain environments.
As a powerful data-driven approach, Multi-Agent Reinforcement Learning (MARL) enables agents to learn and adapt in dynamic and uncertain environments. However, MARL techniques introduce complexities related to communication, coordination, and synchronization among agents. In this PhD research, we investigate autonomous control for smart grid decision networks using MARL. First, we examine the issue of imperfect state information, which frequently arises due to the inherent uncertainties and limitations in observing the system state.
Second, we focus on the cooperative behavior of agents in distributed MARL frameworks, particularly under the central training with decentralized execution (CTDE) paradigm. We provide theoretical results and variance analysis for stochastic and deterministic cooperative MARL algorithms, including Multi-Agent Deep Deterministic Policy Gradient (MADDPG), Multi-Agent Proximal Policy Optimization (MAPPO), and Dueling MAPPO. These analyses highlight how coordinated learning can improve system-wide decision-making in uncertain and dynamic environments like EV networks.
Third, we address the scalability challenge in large-scale NCPS by introducing a hierarchical MARL framework based on a cluster-based architecture. This framework organizes agents into coordinated subgroups, improving scalability while preserving local coordination. We conduct a detailed variance analysis of this approach to demonstrate its effectiveness in reducing communication overhead and learning complexity. This analysis establishes a theoretical foundation for scalable and efficient control in large-scale smart grid applications.
Past Defense Notices
Sandip Dey
Analysis of Performance Overheads in DynamoRIO Binary TranslatorWhen & Where:
2001 B Eaton Hall
Committee Members:
Prasad Kulkarni, ChairJerzy Grzymala-Busse
Esam Eldin Mohamed Aly
Abstract
Dynamic binary translation is the process of translating instruction code from one architecture to another while it executes, i.e., dynamically. As modern applications are becoming larger, more complex and more dynamic, the tools to manipulate these programs are also becoming increasingly complex. DynamoRIO is one such dynamic binary translation tool that targets the most common IA-32 (a.k.a. x86) architecture on the most popular operating systems - Windows and Linux. DynamoRIO includes applications ranging from program analysis and understanding to profiling, instrumentation, optimization, improving software security, and more. However, even considering all of these optimization techniques, DynamoRIO still has the limitations of performance and memory usage, which restrict deployment scalability. The goal of my thesis is to break down the various aspects which contribute to the overhead burden and evaluate which factors directly contribute to this overhead. This thesis will discuss all of these factors in further detail. If the process can be streamlined, this application will become more viable for widespread adoption in a variety of areas. We have used industry standard Mi benchmarks in order to evaluate in detail the amount and distribution of the overhead in DynamoRIO. Our statistics from the experiments show that DynamoRIO executes a large number of additional instructions when compared to the native execution of the application. Furthermore, these additional instructions are involved in building the basic blocks, linking, trace creation, and resolution of indirect branches, all of which in return contribute to the frequent exiting of the code cache. We will discuss in detail all of these overheads, show statistics of instructions for each overhead, and finally show the observations and analysis in this defense.
Eric Schweisberger
Optical Limiting via Plasmonic Parametric AbsorbersWhen & Where:
2001 B Eaton Hall
Committee Members:
Alessandro Salandrino , ChairKenneth Demarest
Rongqing Hui
Abstract
Optical sensors are increasingly prevalent devices whose costs tend to increase with their sensitivity. A hike in sensitivity is typically associated with fragility, rendering expensive devices vulnerable to threats of high intensity illumination. These potential costs and even security risks have generated interest in devices that maintain linear transparency under tolerable levels of illumination, but can quickly convert to opaque when a threshold is exceeded. Such a device is deemed an optical limiter. Copious amounts of research have been performed over the last few decades on optical nonlinearities and their efficacy in limiting. This work provides an overview of the existing literature and evaluates the applicability of known limiting materials to threats that vary in both temporal and spectral width. Additionally, we introduce the concept of plasmonic parametric resonance (PPR) and its potential for devising a new limiting material, the plasmonic parametric absorber (PPA). We show that this novel material exhibits a reverse saturable absorption behavior and promises to be an effective tool in the kit of optical limiter design.
Muhammad Saad Adnan
Corvus: Integrating Blockchain with Internet of Things Towards a Privacy Preserving, Collaborative and Accountable, Surveillance System in a Smart CommunityWhen & Where:
246 Nichols Hall
Committee Members:
Bo Luo, ChairAlex Bardas
Fengjun Li
Abstract
The Internet of Things is been a rapidly growing field that offers improved data collection, analysis and automation as solutions for everyday problems. A smart-city is one major example where these solutions can be applied to issues with urbanization. And while these solutions can help improve the quality of live of the citizens, there are always security & privacy risks. Data collected in a smart-city can infringe upon the privacy of users and reveal potentially harmful information. One example is a surveillance system in a smart city. Research shows that people are less likely to commit crimes if they are being watched. Video footage can also be used by law enforcement to track and stop criminals. But it can also be harmful if accessible to untrusted users. A malicious user who can gain access to a surveillance system can potentially use that information to harm others. There are researched methods that can be used to encrypt the video feed, but then it is only accessible to the system owner. Polls show that public opinion of surveillance systems is declining even if they provide increased security because of the lack of transparency in the system. Therefore, it is vital for the system to be able to do its intended purpose while also preserving privacy and holding malicious users accountable.
To help resolve these issues with privacy & accountability and to allow for collaboration, we propose Corvus, an IoT surveillance system that targets smart communities. Corvus is a collaborative blockchain based surveillance system that uses context-based image captioning to anonymously describe events & people detected. These anonymous captions are stored on the immutable blockchain and are accessible by other users. If they find the description from another camera relevant to their own, they can request the raw video footage if necessary. This system supports collaboration between cameras from different networks, such as between two neighbors with their own private camera networks. This paper will explore the design of this system and how it can be used as a privacy-preserving, but translucent & accountable approach to smart-city surveillance. Our contributions include exploring a novel approach to anonymizing detected events and designing the surveillance system to be privacy-preserving and collaborative.
Lumumba Harnett
Reduced Dimension Optimal and Adaptive Mismatch Processing for Interference CancellationWhen & Where:
246 Nichols Hall
Committee Members:
Shannon Blunt, ChairChristopher Allen
Erik Perrins
James Stiles
Richard Hale
Abstract
Interference has been a subject of interest to radars for generations due to its ability to degrade performance. Commercial radars can experience radio frequency (RF) interference from a different RF service (such as radio broadcasting, television broadcasting, communications, satellites, etc.) if it operates simultaneously in the same spectrum. The RF spectrum is a finite asset that is regulated to mitigate interference and maximum resources. Recently, shared spectrum have been proposed to accommodate the growing commercial demand of communication systems. Airborne radars, performing ground moving target indication (GMTI), encounter interference from clutter scattering that may mask slow-moving, low-power targets. Least-squares (LS) optimal and re-iterative minimum-mean square error (RMMSE) adaptive mismatch processing recent advancements are proposed for GMTI and shared spectrum. Each estimation technique reduces sidelobes, provides less signal-to-noise loss, and less resolution degradation than windowing. For GMTI, LS and RMMSE filters are considered with angle-Doppler filters and pre-existing interference cancellation techniques for better detection performance. Application specific reduce rank versions of the algorithms are also introduced for real-time operation. RMMSE is further considered to separate radar and mobile communication systems operating in the same RF band to mitigate interference and information loss.
April Wade
Exploring Properties, Impact, and Deployment Mechanisms of Profile-Guided Optimizations in Static and Dynamic CompilersWhen & Where:
2001 B Eaton Hall
Committee Members:
Prasad Kulkarni, ChairPerry Alexander
Garrett Morris
Heechul Yun
Kyle Camarda
Abstract
Managed language virtual machines (VM) rely on dynamic or just-in-time (JIT) compilation to generate optimized native code at run-time to deliver high execution performance. Many VMs and JIT compilers collect \emph{profile} data at run-time to enable profile-guided optimizations (PGO) that customize the generated native code to different program inputs. PGOs are generally considered integral for VMs to produce high-quality and performant native code. Likewise, many static, ahead-of-time (AOT) compilers employ PGOs to achieve peak performance, though they are less commonly employed in practice.
We propose a study that analyzes and quantifies the performance benefits of PGOs in both AOT and JIT enviroments, understand the importance of profiling data quantity and quality/accuracy to effectively guide PGOs, and assess the impact of individual PGOs on performance. Additionally, we propose an extension of PGOs found in AOT compiler based on specialization and seek to perform a feasibility study to determine its viability.
Luyao Shang
Memory Based LT Encoders for Delay Sensitive CommunicationsWhen & Where:
246 Nichols Hall
Committee Members:
Erik Perrins, ChairShannon Blunt
Taejoon Kim
David Petr
Tyrone Duncan
Abstract
As the upcoming fifth-generation (5G) and future wireless network is envisioned in areas such as augmented and virtual reality, industrial control, automated driving or flying, robotics, etc, the requirement of supporting ultra-reliable low-latency communications (URLLC) is increasingly urgent than ever. From the channel coding perspective, URLLC requires codewords being transported in finite block-lengths. In this regards, we propose novel encoding algorithms and analyze their performance behaviors for the finite-length Luby transform (LT) codes.
Luby transform (LT) codes, the first practical realization and the fundamental core of fountain codes, play a key role in the fountain codes family. Recently, researchers show that the performance of LT codes for finite block-lengths can be improved by adding memory into the encoder. However, this work only utilizes one memory, leaving the possibilities of exploiting and how to exploiting more memories an open problem. To explore this unknown, in this work we propose an entire family of memory based LT encoders, and analyze their performance behaviors thoroughly over binary erasure channels and AWGN channels.
Pushkar Singh Negi
A comparison of global and saturated probabilistic approximations using characteristic sets in mining incomplete dataWhen & Where:
2001 B Eaton Hall
Committee Members:
Jerzy Grzymala-Busse , ChairPrasad Kulkarni
Cuncong Zhong
Abstract
Data mining is an important part of the knowledge discovery process. Data mining helps in finding out patterns across large data sets and establishing relationship through data analysis to solve problems.
Input data sets are often incomplete, i.e., some attribute values are missing. The rough set theory offers mathematical tools to discover patterns hidden in inconsistent and incomplete data. Rough set theory handles inconsistent data by introducing probabilistic approximations. These approximations are combined with an additional parameter (or threshold) called alpha.
The main objective of this project is to compare global and saturated probabilistic approximations using characteristic sets in mining incomplete data. Eight different data sets with 35% missing values were used for experiments. Two different variations of missing values were used, namely, lost values and "do not care" conditions. For rule induction, we implemented the single local probabilistic approximation version of MLEM2. We implemented a rule checker system to verify the accuracy of our generated ruleset by computing the error rate. Along with the rule checker system, the k-fold cross-validation technique was implemented with a value of k as ten to validate the generated rule sets. Finally, a statistical analysis was done for all the approaches using the Friedman test.
Shashank Sambamoorthy
Security Analysis of Android Applications with OWASP Top 10When & Where:
1A Eaton, Dean's conference room
Committee Members:
Jerzy Grzymala-Busse, ChairDrew Davidson
Cuncong Zhong
Abstract
Mobile application security concerns safeguarding mobile apps from threats, such as malware, password cracking, social engineering and other attacks. Application security is crucial for every enterprise, as the business can be developed only with the guarantee that the apps are secure from potential threats. Open Web Application Security Project(OWASP) has compiled a list of top 10 mobile risks, and has formulated a set of guidelines for app development and testing. The objective of my project is to analyze the security risks of android application, using the guidelines from OWASP top 10. With the help of suitable tools, analysis is done to identify the vulnerabilities and threats in android applications, on API 4.4.1. Numerous tools have been used as a part of this endeavor, all of them are open source and freely available. As a part of this project, I have also attempted to demonstrate each of the top 10 risks, using individual android applications. A detailed analysis was performed on each of the top 10 mobile risks, and suitable countermeasures for mitigation was provided. A detailed survey of 100 popular applications from the Google Play store was also performed and the risks were categorized into low, medium and high impact, depending on the level of threats.
Shadi Pir Hosseinloo
Using deep learning methods for supervised speech enhancement in noisy and reverberant environmentsWhen & Where:
246 Nichols Hall
Committee Members:
Shannon Blunt, ChairJonathan Brumberg
Erik Perrins
Sara Wilson
John Hansen
Abstract
In real world environments, the speech signals received by our ears are usually a combination of different sounds that include not only the target speech, but also acoustic interference like music, background noise, and competing speakers. This interference has negative effect on speech perception and degrades the performance of speech processing applications such as automatic speech recognition (ASR), speaker identification, and hearing aid devices. One way to solve this problem is using source separation algorithms to separate the desired speech from the interfering sounds. Many source separation algorithms have been proposed to improve the performance of ASR systems and hearing aid devices, but it is still challenging for these systems to work efficiently in noisy and reverberant environments. On the other hand, humans have a remarkable ability to separate desired sounds and listen to a specific talker among noise and other talkers. Inspired by the capabilities of human auditory system, a popular method known as auditory scene analysis (ASA) was proposed to separate different sources in a two stage process of segmentation and grouping. The main goal of source separation in ASA is to estimate time frequency masks that optimally match and separate noise signals from a mixture of speech and noise. In this work, multiple algorithms are proposed to improve upon source separation in noisy and reverberant acoustic environment. First, a simple and novel algorithm is proposed to increase the discriminability between two sound sources by scaling (magnifying) the head-related transfer function of the interfering source. Experimental results from applications of this algorithm show a significant increase in the quality of the recovered target speech. Second, a time frequency masking-based source separation algorithm is proposed that can separate a male speaker from a female speaker in reverberant conditions by using the spatial cues of the source signals. Furthermore, the proposed algorithm has the ability to preserve the location of the sources after separation. Three major aims are proposed for supervised speech separation based on deep neural networks to estimate either the time frequency masks or the clean speech spectrum. Firstly, a novel monaural acoustic feature set based on a gammatone filterbank is presented to be used as the input of the deep neural network (DNN) based speech separation model, which shows significant improvement in objective speech intelligibility and speech quality in different testing conditions. Secondly, a complementary binaural feature set is proposed to increase the ability of source separation in adverse environment with non-stationary background noise and high reverberation using 2-channel recordings. Experimental results show that the combination of spatial features with this complementary feature set improves significantly the speech intelligibility and speech quality in noisy and reverberant conditions. Thirdly, a novel dilated convolution neural network is proposed to improve the generalization of the monaural supervised speech enhancement model to different untrained speakers, unseen noises and simulated rooms. This model increases the speech intelligibility and speech quality of the recovered speech significantly, while being computationally more efficient and requiring less memory in comparison to other models. In addition, the proposed model is modified with recurrent layers and dilated causal convolution layers for real-time processing. This model is causal which makes it suitable for implementation in hearing aid devices and ASR system, while having fewer trainable parameters and using only information about previous time frames in output prediction. The main goal of the proposed algorithms are to increase the intelligibility and the quality of the recovered speech from noisy and reverberant environments, which has the potential to improve both speech processing applications and signal processing strategies for hearing aid and cochlear implant technology.
Mustafa AL-QADI
Spectral Properties of Phase Noises and the Impact on the Performance of Optical InterconnectsWhen & Where:
246 Nichols Hall
Committee Members:
Ron Hui, ChairChristopher Allen
Victor Frost
Erik Perrins
Jie Han
Abstract
The non-ending growth of data traffic resulting from the continuing emergence of Internet applications with high data-rate demands sets huge capacity requirements on optical interconnects and transport networks. This requires the adoption of optical communication technologies that can make the best possible use of the available bandwidths of electronic and electro-optic components to enable data transmission with high spectral efficiency (SE). Therefore, advanced modulation formats are required to be used in conjunction with energy-efficient and cost-effective transceiver schemes, especially for medium- and short-reach applications. Important challenges facing these goals are the stringent requirements on the characteristics of optical components comprising these systems, especially laser sources. Laser phase noise is one of the most important performance-limiting factors in systems with high spectral efficiency. In this research work, we study the effects of the spectral characteristics of laser phase noise on the characterization of lasers and their impact on the performance of digital coherent and self-coherent optical communication schemes. The results of this study show that the commonly-used metric to estimate the impact of laser phase noise on the performance, laser linewidth, is not reliable for all types of lasers. Instead, we propose a Lorentzian-equivalent linewidth as a general characterization parameter for laser phase noise to assess phase noise-related system performance. Practical aspects of determining the proposed parameter are also studied and its accuracy is validated by both numerical and experimental demonstrations. Furthermore, we study the phase noises in quantum-dot mode-locked lasers (QD-MLLs) and assess the feasibility of employing these devices in coherent applications at relatively low symbol rates with high SE. A novel multi-heterodyne scheme for characterizing the phase noise of laser frequency comb sources is also proposed and validated by experimental results with the QD-MLL. This proposed scheme is capable of measuring the differential phase noise between multiple spectral lines instantaneously by a single measurement. Moreover, we also propose an energy-efficient and cost-effective transmission scheme based on direct detection of field-modulated optical signals with advanced modulation formats, allowing for higher SE compared to the current pulse-amplitude modulation schemes. The proposed system combines the Kramers-Kronig self-coherent receiver technique, with the use of QD-MLLs, to transmit multi-channel optical signals using a single diode laser source without the use of the additional RF or optical components required by traditional techniques. Semi-numerical simulations based on experimentally captured waveforms from practical lasers show that the proposed system can be used even for metro scale applications. Finally, we study the properties of phase and intensity noise changes in unmodulated optical signals passing through saturated semiconductor optical amplifiers for intensity noise reduction. We report, for the first time, on the effect of phase noise enhancement that cannot be assessed or observed by traditional linewidth measurements. We demonstrate the impact of this phase noise enhancement on coherent transmission performance by both semi-numerical simulations and experimental validation.