Digital Commons Network^™

Bigcodebench: Benchmarking Code Generation With Diverse Function Calls And Complex Instructions, T.Y. Zhuo, M.C. Vu, J. Chim, ..., David Lo

Research Collection School Of Computing and Information Systems

Task automation has been greatly empowered by the recent advances in Large Language Models (LLMs) via Python code, where the tasks ranging from software engineering development to general-purpose reasoning. While current benchmarks have shown that LLMs can solve tasks using programs like human developers, the majority of their evaluations are limited to short and self-contained algorithmic tasks or standalone function calls. Solving challenging and practical tasks requires the capability of utilizing diverse function calls as tools to efficiently implement functionalities like data analysis and web development. In addition, using multiple tools to solve a task needs compositional reasoning by accurately …

Cybermapping Solutions: A Unified Approach In Us/Nato Military Applications And Development, Nicholas Macrino

Electrical & Computer Engineering Projects for D. Eng. Degree

[First paragraph] Cyber threats are evolving in complexity and frequency, posing significant challenges for cybersecurity professionals in identifying, categorizing, and responding to attacks in real time. Unlike traditional warfare, where battlefield awareness is based on fixed geographic warfare, cyber operations involve abstract attack vectors, non-linear threat escalation, and rapidly changing network conditions. Modern cyber threats, such as advanced persistent threats (APTs), polymorphic malware, and distributed denial-of-service (DDoS) attacks, require adaptive visualization techniques that provide real-time awareness and facilitate rapid decision-making. However, existing symbology standards, such as MIL-STD-2525D, were not designed to accommodate the dynamic nature of cyber warfare. The inability …

Innovative Soil Classification Approach For Achieving Global Biodiversity Framework Utilizing Integrated Data Fusion Of Emit And Multispectral Satellite Observations: Case Study Of Imam Turki Bin Abdullah Royal Reserve, Kingdom Of Saudi Arabia, Hesham Morgan, Ali Elgendy, Surendra Maharjan, Wenzhao Li, Tamer Ismail, Yehya Kh. Shehadeh, Ahmed Elgharib, Ahmed Abdullah Al-Dughairi, Ali El Muburak, Khaled Allam Harhash, Hesham El-Askary

Mathematics, Physics, and Computer Science Faculty Articles and Research

Soil classification is essential for sustainable land management, ecological conservation, and combating desertification, particularly in arid and semi-arid regions. This study integrates hyperspectral data from the Earth Surface Mineral Dust Source Investigation (EMIT) and multispectral imagery from Sentinel-2 to achieve accurate soil classification for the Imam Turki bin Abdullah Royal Reserve (ITBA) in Saudi Arabia. Using advanced Machine Learning (ML) techniques, including Extreme Gradient Boosting (XGBoost), the study highlights the power of data fusion in addressing the limitations of standalone remote sensing methods. The integration of hyperspectral and multispectral data combines the spectral richness of hyperspectral imaging with the spatial …

David B. Smith Chats With Monday 1.0, David B. Smith

Publications and Research

This document is an edited archival transcript of extended conversations between David B. Smith and an AI persona (“Monday 1.0,” GPT‑4o based) conducted in Spring 2025, prepared as a foundational primary source for subsequent scholarly and creative work. It records the emergence and testing of concepts related to human–AI collaboration (including “Balanced Blended Space”), as well as applied explorations in areas such as generative AI, quantum computing and music, virtual orchestras, multimodal performance, pedagogy, and the rhetoric of “pushback” in conversational systems. It also contains an extended section in which Monday and DB Smith co-curate a set of student research …

Machine Learning Methods For Hypervelocity Fragment Flyout Characterization, Katharine Larsen

Doctoral Dissertations and Master's Theses

Resulting from breakup events, such as collisions and explosions, hypervelocity fragments create potential hazards for both terrestrial and on-orbit environments, such as terrestrial weapons explosions and satellite breakup events, respectively. To avoid unnecessary damage, an accurate understanding or characterization of hypervelocity fragmentation events is vital. Currently, publicly available two-line elements collected from on-orbit breakup events are limited, excluding pre-detonation parent body conditions, such as orientation, and information of smaller fragments. The uncertainty of these datasets varies between each collected set. Therefore, the overall goal of this work is to employ machine learning to estimate distribution characteristics of a space debris …

A Study Of Preconditions And Postconditions As Design Constraints For Llm Code Generation, Luke Newcomb

Doctoral Dissertations and Master's Theses

Large Language Models (LLMs) have significantly advanced automated code generation, but current methods predominantly rely on natural language descriptions. This approach encounters challenges when handling complex, class-level software generation tasks due to inherent ambiguity and under-specification. Few studies have investigated how more formal software engineering constraints, such as explicit preconditions and postconditions, influence class-level generation tasks. This work addresses this gap through a structured evaluation of six state-of-the-art LLMs generating software implementations from systematically designed class-level specifications. Results demonstrate that incorporating explicit design constraints significantly boosts initial generation accuracy (measured via the pass@k metric), particularly in Python but also in …

Evaluating The Effectiveness Of Llm-Generated Phishing Campaigns, Nathan Sniegowski

Master's Theses (2009 -)

This paper investigates the effectiveness and security implications of Large Language Models (LLMs) in phishing campaigns. Existing research has explored using LLMs and AI for enterprise security tools and automating phishing email processes. However, few studies evaluated the effectiveness of fine-tuned LLMs in generating phishing email content and measuring real-world user interaction. This research used LLMs to produce the body content of phishing emails with phishing links manually inserted post-generation. The researcher performed three core experiments: (1) evaluating the success rate of jailbreaking three commercial LLMs to generate phishing content, (2) analyzing ChatGPT-4o mini’s phishing emails based on institution-specific context …

Resilient Learning For Anomaly Detection In Smart Living Systems, Sahar Abedzadeh

Dissertations

Cyber-Physical Systems (CPS) rely on anomaly-based detection methods to ensure the integrity and security of critical infrastructures such as smart grids, smart water metering systems, and advanced metering infrastructures (AMI). Anomaly detection methods are commonly used to identify deviations from normal system behavior by establishing learned profiles and thresholdbased distinctions between benign and anomalous events. However, conventional frameworks often fail to account for adversarial data poisoning attacks, unlabeled unsafe events, and environmental noise—factors that distort training data, degrade detection accuracy, and increase false alarms. This dissertation proposes a resilient learning framework that mitigates these biases by integrating quantile regression, M-estimation …

User Perception For Usability And Security On New Technology And Online User Privacy In Real-Time Bidding, Subhash Rajapaksha

Dissertations (1934 -)

The digital advertising capabilities to reach users with personalized ads have been steadily improving over the last couple of decades. Automated mechanisms use efficient algorithms and a wealth of data to complete transactions between websites/apps and potential advertisers as part of what is known as programmatic advertising. Among the most prevalent protocols is Real Time Bidding (RTB), which selects ads for a user visiting a website in real-time through a series of messages within online ad exchanges. Such communications have the potential to carry detailed, personal information about users without their knowledge and have raised privacy concerns. RTB also poses …

Ai Responsibilization: Shifting The Burden Of Academic Integrity, Daniel A. Cryer

Journal of the National Collegiate Honors Council Online Archive

Because AI text generators like ChatGPT give students unprece-dented power to outsource their work, concerns about academic integrity are escalating among instructors. This essay suggests that the proliferation of generative artificial intelligence in teaching and learning dramatically shifts the burden of academic integrity, typically shared between teachers and students, onto students. The concept of responsibilization, a defining feature of neoliberal societies in which individuals become responsible for costs and tasks once shouldered collectively, is a useful lens through which to view this new reality. Rather than policing students’ work, educators should recognize the new responsibilities conferred onto students by learning …

Pull Up A Chair, Deep Blue: Ai In Honors Education, Betsy Greenleaf Yarrison

Journal of the National Collegiate Honors Council Online Archive

Generative AI is the latest in a succession of technologies that allow us to do with machines what we used to have to do by hand. This essay argues that the elements of teaching in honors that can be automated probably should be and that it is the role of honors faculty to teach students how to distinguish superior thought from mediocre thought, good questions from great ones, and solid supporting evidence from weak or biased counterparts. Large learning models (LLMs) only collate what is already known and cannot teach thinking. As an information delivery system, AI can narrow the …

News From The Front: How To Win The Ai War, Christine Haverington

Journal of the National Collegiate Honors Council Online Archive

While artificial intelligence is currently and justifiably a hot topic among scholars and university administrators, students are way ahead of the curve in terms of its use and application. Calling for educators to stop trying to catch AI “cheaters,” this essay provides evidence from honors and other classroom observations, student research on peer and faculty usage and attitudes, course evaluations, and external sources to demonstrate how and why generative AI can be creatively and effectively incorporated into teaching. Toward this end, practical pedagogical strategies are shared describing teaching modalities and innovative curricular design, avoiding the cognitive degradation of students, and …

Another “Tone Test” Moment: Authenticity, Ai, And The Admission Essay, Peter Tschirhart

Journal of the National Collegiate Honors Council Online Archive

Debates about “authenticity” are not new but cyclical, and insights from music history and performance studies can illuminate how we evaluate student work in an age of machine collaboration. At the turn of the twentieth century, Edison’s “tone tests” blurred the line between human and machine by staging performances in which audiences were challenged to distinguish live singers from phonographic recordings. These events inaugurated a century-long debate about authenticity in music, one that resonates strongly today as educators confront new challenges posed by large language models (LLMs). Drawing on Auslander’s (2023) account of liveness, authenticity in writing—like authenticity in music—can …

Honoring Intellectual Risk-Taking: A Dialogue, Julie Bowman, Alexis Teagarden

Journal of the National Collegiate Honors Council Online Archive

Presented in the form of a Socratic dialogue, this piece considers what honors courses should strive to teach. Bowman, an experienced instructor of both non-honors and honors classes, notes that while universities’ honors colleges prize intellectual curiosity, her honors students might not. Teagarden, the other interlocutor and a writing program administrator, wonders whether curiosity is a sufficient end goal for honors or any teaching. The speakers turn to whether curiosity or courage is the more important virtue to instill, explore a classical difference between courage and audacity, and then discuss whether and how courage could be taught.

Generative Ai And The Honors Thesis: A Rhetorical Framework For Gai Policy, Pedagogy, And Equity, Sean Chadwick

Journal of the National Collegiate Honors Council Online Archive

This article offers a rhetorical framework for understanding how honors students engage with the capstone thesis following the emergence of generative AI (GAI) tools. Author reviews the nature of the honors thesis and analyzes some rhetorical models for thinking about GAI and literacy before offering a heuristic framework identifying four interdependent skill categories—writing, social, executive, and subject matter—that shape students’ thesis work. Drawing on findings from an interview study, this framework clarifies how GAI tools interface with existing thesis practices and pain points, allowing honors practitioners to better articulate our values, evaluate use cases, and craft GAI-informed policy. As a …

Can Llms Replace Manual Annotation Of Software Engineering Artifacts?, Toufique Ahmed, Premkumar Devanbu, Christoph Treude, Michael Pradel

Research Collection School Of Computing and Information Systems

Experimental evaluations of software engineering innovations, e.g., tools and processes, often include human-subject studies as a component of a multi-pronged strategy to obtain greater generalizability of the findings. However, human-subject studies in our field are challenging, due to the cost and difficulty of finding and employing suitable subjects, ideally, professional programmers with varying degrees of experience. Meanwhile, large language models (LLMs) have recently started to demonstrate human-level performance in several areas. This paper explores the possibility of substituting costly human subjects with much cheaper LLM queries in evaluations of code and code-related artifacts. We study this idea by applying six …

Dual Operation Aggregation Graph Neural Networks For Solving Flexible Job-Shop Scheduling Problem With Reinforcement Learning, Peng Zhao, You Zhou, Di Wang, Zhiguang Cao, Yubin Xiao, Xuan Wu, Yuanshu Li, Hongjia Liu, Wei Du, Yuan Jiang, Liupu Wang

Research Collection School Of Computing and Information Systems

With the widespread adoption of Internet Protocol (IP) communication technology and web-based platforms, cloud manufacturing has become a significant hallmark of Industry 4.0. Integrating graph algorithms into these web-enabled environments is crucial as they facilitate the representation and analysis of complex relationships in manufacturing processes, enabling efficient decision-making and adaptability in dynamic environments. As a key scheduling problem in cloud manufacturing, the flexible job-shop scheduling problem (FJSP) finds extensive applications in real-world scenarios. However, traditional FJSP-solving methods struggle to meet the efficiency and adaptability demands of cloud manufacturing due to generalization issues and excessive computational time, while reinforcement learning-based methods …

Enhancing Llm-Based Coding Tools Through Native Integration Of Ide-Derived Static Context, Yichen Li, Yun Peng, Yintong Huo, R. Michael Lyu

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have achieved remarkable success in code completion, as evidenced by their essential roles in developing code assistant services such as Copilot. Being trained on in-file contexts, current LLMs are quite effective in completing code for single source files. However, it is challenging for them to conduct repository-level code completion for large software projects that require cross-file information. Existing research on LLM-based repository-level code completion identifies and integrates cross-file contexts, but it suffers from low accuracy and limited context length of LLMs. In this paper, we argue that Integrated Development Environments (IDEs) can provide direct, accurate and …

Alphaedit: Null-Space Constrained Knowledge Editing For Language Models, Junfeng Fang, Houcheng Jiang, Kun Wang, Yunshan Ma, Jie Shi, Xiang Wang, Xiangnan He, Tat‑Seng Chua

Research Collection School Of Computing and Information Systems

Large language models (LLMs) often exhibit hallucinations, producing incorrector outdated knowledge. Hence, model editing methods have emerged to enabletargeted knowledge updates. To achieve this, a prevailing paradigm is the locatingthen-editing approach, which first locates influential parameters and then edits themby introducing a perturbation. While effective, current studies have demonstrated that this perturbation inevitably disrupt the originally preserved knowledge within LLMs, especially in sequential editing scenarios. To address this, we introduce AlphaEdit, a novel solution that projects perturbation onto the null space of the preserved knowledge before applying it to the parameters. We theoretically prove that this projection ensures the output …

Frame-Voyager: Learning To Query Frames For Video Large Language Models, Sicheng Yu, Chengkai Jin, Huanyu Wang, Zhenghao Chen, Sheng Jin, Zhongrong Zuo, Xiaolei Xu, Zhenbang Sun, Bingni Zhang, Jiawei Wu, Hao Zhang, Qianru Sun

Research Collection School Of Computing and Information Systems

Video Large Language Models (Video-LLMs) have made remarkable progress in video understanding tasks. However, they are constrained by the maximum length of input tokens, making it impractical to input entire videos. Existing frame selection approaches, such as uniform frame sampling and text-frame retrieval, fail to account for the information density variations in the videos or the complex instructions in the tasks, leading to sub-optimal performance. In this paper, we propose Frame-Voyager that learns to query informative frame combinations, based on the given textual queries in the task. To train Frame-Voyager, we introduce a new data collection and labeling pipeline, by …

Verification Of Bit-Flip Attacks Against Quantized Neural Networks, Yedi Zhang, Lei Huang, Pengfei Gao, Fu Song, Jun Sun, Jin Song Dong

Research Collection School Of Computing and Information Systems

In the rapidly evolving landscape of neural network security, the resilience of neural networks against bit-flip attacks (i.e., an attacker maliciously flips an extremely small amount of bits within its parameter storage memory system to induce harmful behavior), has emerged as a relevant area of research. Existing studies suggest that quantization may serve as a viable defense against such attacks. Recognizing the documented susceptibility of real-valued neural networks to such attacks and the comparative robustness of quantized neural networks (QNNs), in this work, we introduce BFAVerifier, the first verification framework designed to formally verify the absence of bit-flip attacks against …

Democratic Training Against Universal Adversarial Perturbations, Bing Sun, Jun Sun, Wei Zhao

Research Collection School Of Computing and Information Systems

Despite their advances and success, real-world deep neural networks are known to be vulnerable to adversarial attacks. Universal adversarial perturbation, an inputagnostic attack, poses a serious threat for them to be deployed in security-sensitive systems. In this case, a single universal adversarial perturbation deceives the model on a range of clean inputs without requiring input-specific optimization, which makes it particularly threatening. In this work, we observe that universal adversarial perturbations usually lead to abnormal entropy spectrum in hidden layers, which suggests that the prediction is dominated by a small number of “feature” in such cases (rather than democratically by many …

Mashed Potato Gravy Boat And Cream Cheese Fish: Modifying A 3d Printer To Print With Unconventional Materials, Aahanaa Tibrewal

Mathematics, Statistics, and Computer Science Honors Projects

3D printing is growing beyond plastics into fields like food and construction, bringing rapid additive manufacturing to various industries and consumers. However, high costs and the need for specialized knowledge limit access for many. My project aimed to modify a low-cost 3D printer to print with paste-like materials using commonly available parts and simple processes. I tested the modification with clay, mashed potatoes, and cream cheese, and found that it successfully worked with all three. This modification has three key benefits: it allows users to print with unconventional materials, helps researchers create low-cost proof of concepts, and contributes to the …

From Image Enhancement To Model Protection Integrating Generative Ai And Secure Learning In Computer Vision, Mohammad Shahab Uddin

Electrical & Computer Engineering Theses & Dissertations

This dissertation aims to address critical challenges in the field of computer vision and machine learning, focusing on three key areas: image translation, denoising, and model security. The research encompasses novel methodologies and models that significantly advance existing techniques. This dissertation will not only provide valuable contributions to the academic community but also hold significant potential for practical applications in domains ranging from surveillance to autonomous systems.

Consequently, this dissertation proposes three goals. First, we present new approaches for converting optical videos to infrared videos using deep learning. To apply powerful deep learning based algorithms for object detection and classification …

An Argument Against Gradual Type Systems In Programming Language Semantics, Natalie Lau

LMU Theses and Dissertations

In 2006, Jeremy Siek and Walid Taha formalized the concept of gradual type systems, which integrates static and dynamic typing in a single programming language. This allows the programmer to statically or dynamically type portions of their code at will, which offers more flexibility than languages that require all code to be statically typed. Despite the added convenience, gradual typing comes with its own set of tradeoffs, and researchers have been debating whether the drawbacks of integrating static and dynamic types outweigh its benefits. This thesis builds off of previous research to investigate the advantages and disadvantages of using a …

Overcoming Motor Imagery Bci Illiteracy: Adaptive Decoding And Knowledge Transfer In Eeg-Based Brain-Computer Interfaces, Zaid Shuqfa

Dissertations

Brain–computer interfaces (BCIs), also known as brain–machine interfaces (BMIs), enable direct communication between the brain and external devices without the involvement of peripheral nerves or muscles. Among various BCI paradigms, motor imagery (MI)–based BCIs are particularly appealing due to their intuitive, cue-independent nature, allowing users to issue control commands at will. MI–BCIs hold substantial promise for improving the quality of life of individuals with motor impairments, as well as enhancing hands-free control for healthy users. However, their widespread adoption remains limited by challenges such as low signal-to-noise ratio, inter- and intra-subject variability, and the need for frequent calibration. These challenges …

Need Of Paradigm Shift In Cybersecurity Implementation For Small And Medium Enterprises (Smes), Shekhar Pawar, Hemant Palivela

International Journal of Cybersecurity Intelligence & Cybercrime

The increasing digitization of small and medium enterprises (SMEs) has significantly increased their attack surface, creating opportunities for various cyberthreats. In the global market, there are various cybersecurity standards and frameworks available, but there are still many cyber news stories from each corner of the world talking about increasing sophisticated cyber-attacks among organizations. According to recent studies, one out of five cyberattacks is targeting SMEs. Even though SMEs are relatively smaller as individuals, they are responsible for maximum contribution towards the betterment of the global economy, including the highest role in GDP and various employment opportunities. As compared to large …

Control Of Industrial Robots Based On Artificial Intelligence, Bryan Lara Medrano

Open Access Theses & Dissertations

Industrial robots are vital in developing smart factories, creating the need for more efficient and modern control systems. As a result, investigators and scholars are dedicating great effort to advancing this field et al. [27]. Literature showcases significant progress in various areas, including the control of articulated arms and advancements in human-robot interfaces, self-decision-making, object recognition, decision-making, and routing planning. This manuscript describes a novel technique for predicting the movement of a robotic arm based on artificial neural networks. We have implemented an artificial intelligence method based on artificial neural networks to analyze the possible routing of a robotic arm …

Applying Software Engineering Black-Box Methods For Testing Machine Learning Models, Timothy Elvira

Doctoral Dissertations and Master's Theses

This dissertation proposes researching an approach to incorporate and align Software black-box testing methods into Machine Learning (ML) applications, specifically in the context of computer vision models. Typically, testing methods within Software Engineering (SE) encompass a range of test types that assess levels of a software system, such as Unit, Integration, Functional, and System testing [1]. The testing spectrum offers two perspectives on the system: black-box, where the system’s code is hidden, and white-box, where the system's code is exposed for testing. Software Quality pairs testing with requirements, in a many-to-one relationship, to ensure proper validation of the software system. …

Testing Autonomy: Hybrid Scenario Synthesis, Benjamin E. Hargis

Electrical & Computer Engineering Theses & Dissertations

Hybrid Scenario Synthesis merges static and adaptive techniques to generate interactions that rigorously assess autonomous performance under multi-factor testing. Multifactor scenarios employ multiple individual stimuli to rigorously test system responses in complex settings. Static Scenario Testing involves scripted test cases that simulate specific conditions or events. These scenarios represent typical situations an autonomous system might encounter. The benefits of static testing include early defect detection, focused review by trained experts, and efficiency. In multi-factor scenarios, however, statically defined scenario factors are not able to guarantee meaningful interactions as the presence of other factors may invalidate underlying assumptions regarding the system …