Digital Commons Network^™

Where Did It Go Wrong? Attributing Undesirable Llm Behaviors Via Representation Gradient Tracing, Zhe Li, Wei Zhao, Yige Li, Jun Sun

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their deployment is frequently undermined by undesirable behaviors such as generating harmful content, factual inaccuracies, and societal biases. Diagnosing the root causes of these failures poses a critical challenge for AI safety. Existing attribution methods, particularly those based on parameter gradients, often fall short due to prohibitive noisy signals and computational complexity. In this work, we introduce a novel and efficient framework that diagnoses a range of undesirable LLM behaviors by analyzing representation and its gradients, which operates directly in the model's activation space to provide a semantically meaningful signal linking …

Llmqua: Practical Backdoor Injection On Large Language Model Quantization, Xiangxiang Chen, Peixin Zhang, Jun Sun, Jin Song Dong, Wenhai Wang, Jingyi Wang

Research Collection School Of Computing and Information Systems

Quantization is widely used to enable local deployment of large language models (LLMs) on resource-constrained devices. Recent work (e.g., QuRA) shows quantization can be exploited via rounding manipulation to implant backdoors. However, such an attack has been evaluated only on small models and does not directly apply to LLMs due to three key constraints: (1) limited poisoning data from small, task-agnostic calibration sets; (2) layer-wise quantization restricting adversarial access to global representations; and (3) lack of gradient access in quantization pipelines, blocking gradient-based attacks.We propose LLMQuA, a practical quantization-phase backdoor attack tailored to the LLM setting. LLMQuA (i) injects backdoors …

Prompting Frameworks For Large Language Models: A Survey, Xiaoxia Liu, Jingyi Wang, Jun Sun, Xiaohan Yuan, Guoliang Dong, Peng Di, Wenhai Wang, Dongxia Wang

Research Collection School Of Computing and Information Systems

Since the launch of ChatGPT, a powerful AI Chatbot developed by OpenAI, large language models (LLMs) have made significant advancements in both academia and industry, bringing about a fundamental engineering paradigm shift in many areas. While LLMs are powerful, it is also crucial to best use their power where “prompt” plays a core role. However, the booming LLMs themselves, including excellent APIs like ChatGPT, have several inherent limitations: (1) temporal lag of training data, and (2) the lack of physical capabilities to perform external actions. Recently, we have observed the trend of utilizing prompt-based tools to better utilize the power …

Bridging Bug Localization And Issue Fixing: A Hierarchical Localization Framework Leveraging Large Language Models, Jianming Chang, Xin Zhou, Lulu Wang, David Lo, Bixin Li

Research Collection School Of Computing and Information Systems

Automated issue fixing is a critical task in software debugging and has recently garnered significant attention from academia and industry. However, existing fixing techniques predominantly focus on the repair phase, often overlooking the importance of improving the preceding bug localization phase. As a foundational step in issue fixing, bug localization plays a pivotal role in determining the overall effectiveness of the entire process. To enhance the precision of issue fixing by accurately identifying bug locations in large-scale projects, this paper presents BugCerberus, the first hierarchical bug localization framework powered by three customized large language models. First, BugCerberus analyzes intermediate representations …

On Autopilot? An Empirical Study Of Human-Ai Teaming And Review Practices In Open Source, Haoyu Gao, Peerachai Banyongrakkul, Hao Guan, Mansooreh Zahedi, Christoph Treude

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) increasingly automate software engineering tasks. While recent studies highlight the accelerated adoption of “AI as a teammate” in Open Source Software (OSS), developer interaction patterns remain under-explored. In this work, we investigated project-level guidelines and developers’ interactions with AI-assisted pull requests (PRs) by expanding the AIDev dataset to include finer-grained contributor code ownership and a comparative baseline of human-created PRs. We found that over 67.5% of AI-co-authored PRs originate from contributors without prior code ownership. Despite this, the majority of repositories lack guidelines for AI-coding agent usage. Notably, we observed a distinct interaction pattern: AI-co-authored PRs …

Structural Silence: When Ai Infrastructure Fails Speakers Of Underrepresented Languages, Avijit Roy, Proma Roy

Publications and Research

Artificial intelligence tools for education and language support are increasingly framed as scalable responses to access gaps in under-resourced communities. Yet the infrastructure underlying these tools—training corpora, tokenization schemes, evaluation benchmarks, and deployment architectures—encodes a set of assumptions that systematically disadvantages speakers of underrepresented languages before a single model is trained. This paper examines those assumptions through the lens of Bengali, one of the world’s most widely spoken languages with roughly 285 million speakers (Ethnologue, 2025; International Communication and Leadership School, 2026), and the structural barriers that emerge when attempting to build AI-assisted educational tools for Bengali-speaking learners in low-connectivity …

Weakly Supervised Video Anomaly Detection And Localization With Spatio-Temporal Prompts, Peng Wu, Xuerong Zhou, Guansong Pang, Zhiwei Yang, Qingsen Yan, Peng Wang, Yanning Zhang

Research Collection School Of Computing and Information Systems

Current weakly supervised video anomaly detection (WSVAD) task aims to achieve frame-level anomalous event detection with only coarse video-level annotations available. Existing works typically involve extracting global features from full-resolution video frames and training frame-level classifiers to detect anomalies in the temporal dimension. However, most anomalous events tend to occur in localized spatial regions rather than the entire video frames, which implies existing frame-level feature based works may be misled by the dominant background information and lack the interpretation of the detected anomalies. To address this dilemma, this paper introduces a novel method called STPrompt that learns spatio-temporal prompt embeddings …

Portrait Shadow Removal Via Self-Exemplar Illumination Equalization, Qian Huang, Cheng Xu, Guiqing Li, Ziheng Wu, Shengxin Liu, Shengfeng He

Research Collection School Of Computing and Information Systems

We introduce the Self-Exemplar Illumination Equalization Network, designed specifically for effective portrait shadow removal. The core idea of our method is that partially shadowed portraits can find ideal exemplars within their non-shadowed facial regions. Rather than directly fusing two distinct classes of facial features, our approach utilizes non-shadowed regions as an illumination indicator to equalize the shadowed regions, generating deshadowed results without boundary-merging artifacts. Our network comprises cascaded Self-Exemplar Illumination Equalization Blocks (SExmBlock), each containing two modules: a self-exemplar feature matching module and a feature-level illumination rectification module. The former identifies and applies internal illumination exemplars to shadowed areas, producing …

Managing Reproducibility Debt In Scientific Software: A Practical Framework, Zara Hassan, Christoph Treude, Graham Williams, Michael Norrish, Alex Potanin

Research Collection School Of Computing and Information Systems

Scientific software includes end-user applications, modelling tools, research software for publications, and production systems for real users. It plays a key role across various scientific disciplines by enabling large-scale computation, simulation, and data analysis. Unlike commercial software, scientific software is often developed in dynamic research environments with limited engineering practices, documentation, or testing. This makes it fragile and difficult to reproduce results, even when code and data are available, conditions in which Reproducibility Debt (RpD) accumulates. This paper presents the Reproducibility Debt Management Framework (RpD-MF), which is grounded in evidence from a systematic literature review, practitioner interviews, and a global …

Understanding Codebase Like A Professional! Human-Ai Collaboration For Code Comprehension, Jie Gao, Yue Xue, Xiaofei Xie, Junming Cao, Soemin Thant, Erika Lee, Bowen Xu

Research Collection School Of Computing and Information Systems

Understanding an unfamiliar codebase is an essential task for developers in various scenarios, such as during the onboarding process. Especially when the codebase is large and time is limited, achieving a decent level of comprehension remains challenging for both experienced and novice developers, even with the assistance of large language models (LLMs). Existing studies have shown that LLMs often fail to support users in understanding code structures or to provide user-centered, adaptive, and dynamic assistance in real-world settings.To address this, we propose learning from the perspective of a unique role, code auditors, whose work often requires them to quickly familiarize …

Fully Decentralized Hierarchical Federated Learning At The Edge With Post-Quantum Secure Communication, Tariq Qayyum

Dissertations

Federated learning (FL) enables collaborative model training without centralizing raw data, but deploying FL at scale in real edge environments remains challenging because iterative training and aggregation must operate over heterogeneous, resource-constrained, and often mobile devices with time-varying connectivity. Conventional hierarchical federated learning (HFL) partially mitigates communication cost by introducing fog/edge aggregation, yet many designs retain cloud-based global aggregation and cloud-centric coordination. This places wide-area network latency on the critical path of every training round, creates a single point of failure, and limits responsiveness as model sizes and federation scale grow. Moreover, moving coordination and aggregation closer to the edge …

Trustgen: A Platform Of Dynamic Benchmarking On The Trustworthiness Of Generative Foundation Models, Yue Huang, Et. Al

Research Collection School Of Computing and Information Systems

Generative foundation models (GenFMs), such as large language models and text-to-image systems, have demonstrated remarkable capabilities in various downstream applications. As they are increasingly deployed in high-stakes applications, assessing their trustworthiness has become both a critical necessity and a substantial challenge. Existing evaluation efforts are fragmented, rapidly outdated, and often lack extensibility across modalities. This raises a fundamental question: how can we systematically, reliably, and continuously assess the trustworthiness of rapidly advancing GenFMs across diverse modalities and use cases? To address these gaps, we introduce TrustGen, a dynamic and modular benchmarking system designed to systematically evaluate the trustworthiness of GenFMs …

Intelligent Deep Learning-Based Sign Language Translation System, Nada Rasem Shahin

Dissertations

The Deaf and Hard of Hearing (DHH) community uses sign language as a primary means of communication. However, the shortage of sign language interpreters and the existence of hundreds of sign languages limit accessibility and inclusion. Sign Language Machine Translation (SLMT) systems present a promising solution for bridging the communication gap between the DHH and the hearing individuals, supporting inclusive societies. In smart cities, such systems play an essential role in improving the quality of life on a community level. In particular, as the population’s well-being is critical, developing intelligent assistive technologies, such as SLMT systems, is necessary to provide …

A Comparative Study On Performance Of Iot-Driven Ml-Enabled Forecasting Models For Efficient Air Quality Monitoring, Bara Ksiksi

Theses

Air pollution is one of the most critical environmental challenges affecting public health globally, responsible for approximately 4.2 million premature deaths annually according to the World Health Organisation. This thesis presents a comparative study of IoT-driven machine learning forecasting models for air quality monitoring in Abu Dhabi, UAE, introducing a zonal approach combined with satellite-based spatial validation. The primary objective is to evaluate forecasting performance across three distinct activity zones using ground station data from the Environment Agency Abu Dhabi (EAD), and to incorporate a spatial validation component using satellite imagery to assess the consistency of ground-based predictions at a …

Dissecting The Etiology Of Alcohol Use Disorder By An Integrative Heritable Component Approach, Ivy Garrenton

Computer Science Theses & Dissertations

Alcohol Use Disorder (AUD) is a pervasive condition characterized by complex interplay among genetic, phenotypic, and environmental factors. Although previous studies have identi fied genetic loci associated with alcohol consumption, these efforts have not captured the genetic heterogeneity and gene-environment interactions underlying AUD pathogenesis. To address this critical gap, we developed a novel statistical methodology that integrates phenotypic, genotypic, and environmental data through an environmentally modified Genetic Relationship Matrix (GRM) to derive AUD-related traits with enhanced heritability.

This approach demonstrated superior performance in both simulated and real-world datasets. Traits derived using the environmentally modified GRM exhibited significantly higher estimated heritability …

Personality Predictors Of Cybersecurity Vulnerability: Insights From Self-Reports And Stimulated Threat Scenarios, Saroja Roy Grandhi

Psychology Theses & Dissertations

In this cyber dependent and enabled era, understanding the role of human factors in digital security is essential. This study investigates the relationship between Big-Five personality traits and cybersecurity behaviors by examining both self-reported and stimulated behaviors in security threat scenarios. Participants completed validated questionnaires to report their personality traits, cybersecurity practices and engage in task-based stimulations to capture behaviors such as phishing detection, password creation, and response to security alerts. The study tested whether higher conscientiousness, openness, and agreeableness would be associated with stronger cybersecurity practices and smaller discrepancies between self-reported and observed behaviors. And, whether greater extraversion and …

Pushing High-Performance Private Inference Towards Resource-Constrained Edge Clients, Xiangrui Xu

Computer Science Theses & Dissertations

The widespread adoption of Machine Learning as a Service (MLaaS) has enabled resource constrained edge clients, such as mobile and IoT devices, to leverage powerful deep learning mod els hosted on the cloud. However, this paradigm introduces critical privacy challenges regarding the client’s sensitive input data and the server’s proprietary model parameters. While cryptographic techniques like Homomorphic Encryption (HE) and Multi-Party Computation (MPC) enable Private Inference (PI), existing frameworks impose prohibitive computational and communication overheads that render them impractical for edge deployment. This dissertation introduces three novel frameworks—SPOT, LUTless, and PrivShap—to systematically address the efficiency bottlenecks of PI in edge …

Causality-Aware Safety Testing For Autonomous Driving Systems, Wenbing Tang, Mingfei Cheng, Renzhi Wang, Yuan Zhou, Chengwei Liu, Yang Liu, Zuohua Ding

Research Collection School Of Computing and Information Systems

Simulation-based testing is essential for evaluating the safety of Autonomous Driving Systems (ADSs). Comprehensive evaluation requires testing across diverse scenarios that can trigger various types of violations under different conditions. While existing methods typically focus on individual diversity metrics, such as input scenarios, ADS-generated motion commands, and system violations, they often fail to capture the complex interrelationships among these elements. For instance, identical motion commands can produce different collision risks in varying scenes, and the same collision may result from different commands under different scenarios. This oversight leads to gaps in testing coverage, potentially missing critical issues in the ADS …

Developing Blockchain-Based Transparent E-Commerce Solutions For Danish Smes To Promote Sustainable Design Products, Somnath Mazumdar, Robert John Kauffman, Thomas Jensen, Raghava Rao Mukkamala, Jan Damsgaard

Research Collection School Of Computing and Information Systems

Typically, a firm's objectives include establishing consumer confidence, preserving its brand image, and developing a profitable business strategy. Consumers now place greater emphasis on the sustainability and transparency of their purchases. Given environmental and economic limitations, firms are often compelled to implement sustainable production methods. This is especially a struggle for small- and medium-sized enterprises (SMEs) with new technology, as it can increase their risk of failure. This has led to a problem for consumers, who must cross-check the sustainability-related claims of the firms they buy from. This is challenging because of limited process trace data and restricted enforcement capabilities. …

Dragging With Geometry: From Pixels To Geometry-Guided Image Editing, Xinyu Pu, Hongsong Wang, Jie Gui, Pan Zhou

Research Collection School Of Computing and Information Systems

Interactive point-based image editing serves as a controllable editor, enabling precise and flexible manipulation of image content. However, most drag-based methods operate primarily on the 2D pixel plane with limited use of 3D cues. As a result, they often produce imprecise and inconsistent edits, particularly in geometry-intensive scenarios such as rotations and perspective transformations. To address these limitations, we propose a novel geometry-guided drag-based image editing method—GeoDrag, which addresses three key challenges: 1) incorporating 3D geometric cues into pixel-level editing, 2) mitigating discontinuities caused by geometry-only guidance, and 3) resolving conflicts arising from multi-point dragging. Built upon a unified displacement …

Autologger: A Multi-Agent Framework For The End-To-End Automated Logging, Renyi Zhong, Yintong Huo, Wenwei Gu, Yichen Li, Michael R. Lyu

Research Collection School Of Computing and Information Systems

Software logging is critical for system observability, yet developers face a dual crisis of costly overlogging and risky underlogging. Existing automated logging tools often overlook the fundamental whether-to-log decision and struggle with the composite nature of logging. In this paper, we propose AutoLogger, a novel hybrid framework that addresses the complete the end-to-end logging pipeline. AutoLogger first employs a fine-tuned classifier, the Judger, to accurately determine if a method requires new logging statements. If logging is needed, a multi-agent system is activated. The system includes specialized agents: a Locator dedicated to determining where to log, and a Generator focused on …

Who Said Cve? How Vulnerability Identifiers Are Mentioned By Humans, Bots, And Agents In Pull Requests, Pien Rooijendijk, Christoph Treude, Mairieli Wessel

Research Collection School Of Computing and Information Systems

Vulnerability identifiers such as CVE, CWE, and GHSA are standardised references to known software security issues, yet their use in practice is not well understood. This paper compares vulnerability ID use in GitHub pull requests authored by autonomous agents, bots, and human developers. Using the AIDev pop dataset and an augmented set of pull requests from the same repositories, we analyse who mentions vulnerability identifiers and where they appear. Bots account for around 69.1% of all mentions, usually adding few identifiers in pull request descriptions, while human and agent mentions are rarer but span more locations. Qualitative analysis shows that …

Federated Retrieval-Augmented Generation For Cybersecurity In Resource-Constrained Iot And Edge Environments: A Deployment-Oriented Scoping Review, Hangyu He, Yuan, Kai Wu, Wei Ni

Research outputs 2022 to 2026

Cybersecurity operations in IoT and edge environments require fast, evidence-grounded decisions under strict resource and trust constraints. While large language models can support triage and incident analysis, their parametric knowledge may be outdated and prone to hallucination. Retrieval-augmented generation (RAG) improves grounding by conditioning responses on retrieved evidence, but also introduces new risks such as knowledge-base poisoning, indirect prompt injection, and embedding leakage. Federated learning enables collaborative adaptation without centralizing sensitive data, motivating federated RAG (FedRAG) architectures for distributed cybersecurity deployments. This study presents a deployment-oriented scoping review of FedRAG for cybersecurity. The review follows PRISMA-ScR reporting guidance and synthesizes …

Software Engineering In The Age Of Coding Agents: Failure Modes And Rejection Patterns, Mahd Mohd Hindi

Thesis/ Dissertation Defenses

This thesis investigates the real-world behavior of LLM-driven coding agents that generate code changes and submit pull requests (PRs) to public software repositories. As these tools evolve from autocomplete-style assistants into more autonomous agents, their contributions increasingly interact with socio-technical review processes (human reviewers, bots, CI/CD gates, and project norms). This thesis focuses on understanding why agent-generated PRs are accepted or rejected and what these outcomes reveal about current agent limitations in practical development workflows. The main objective of this thesis is to systematically characterize rejection patterns and failure modes of agent-generated pull requests in real repositories. Specifically, the thesis …

Software Engineering In The Age Of Coding Agents: Failure Modes And Rejection Patterns, Mahd Mohd Taysir Hindi

Thesis/ Dissertation Defenses

This thesis investigates the real-world behavior of LLM-driven coding agents that generate code changes and submit pull requests (PRs) to public software repositories. As these tools evolve from autocomplete-style assistants into more autonomous agents, their contributions increasingly interact with socio-technical review processes (human reviewers, bots, CI/CD gates, and project norms). This thesis focuses on understanding why agent-generated PRs are accepted or rejected and what these outcomes reveal about current agent limitations in practical development workflows. The main objective of this thesis is to systematically characterize rejection patterns and failure modes of agent-generated pull requests in real repositories. Specifically, the thesis …

Shine: Multimodal Machine Learning Approaches For Solar Energetic Particles Events Event Prediction And Posthoc Analysis, Soukaina Filali Boubrahimi

Funded Research Records

No abstract provided.

Neutrosophic Probability With Dynamic Temporal Uncertainty (Nptu), Bhimraj Basumatary, Ashoke Kumar Brahma

Neutrosophic Systems with Applications

This paper introduces Neutrosophic Probability with Dynamic Temporal Uncertainty (NPTU), an extension of classical neutrosophic probability that incorporates the dimension of time. In classical neutrosophic probability, the degrees of truth, indeterminacy, and falsity are considered static. However, real-world uncertainties evolve, and their degrees change as new information becomes available. NPTU models these uncertainties dynamically, allowing for more accurate decision-making in time-varying environments. The paper explores key mathematical properties of NPTU, including entropy, distance measures, similarity measures, and Kullback-Leibler (KL) divergence, to quantify and compare temporal uncertainty states. The proposed framework is demonstrated through a case study on stock price prediction, …

Double-Valued Complex Neutrosophic Graphs, Suriyakumar G, V. J. Sudhakar, Takaaki Fujita

Neutrosophic Systems with Applications

This paper introduces a novel graph-theoretic framework, called the double-valued complex neutrosophic graph, as an extension of double-valued neutrosophic set theory. Within this framework, we investigate several important classes of such graphs, including self-complementary, strong, and full double-valued complex neutrosophic graphs, and establish a number of their fundamental properties. To clarify the proposed concepts and demonstrate their structural behavior, several relevant illustrative examples are also provided.

Neutrosophic Sets In Neural Networks: Theory, Applications, And Challenges, Vladimir Simic, Dragan Pamucar, Hafiz Muhammad Athar Farid

Neutrosophic Systems with Applications

The integration of neutrosophic sets into neural networks presents a novel approach to handling uncertainty, indeterminacy, and falsity in data. Traditional neural networks typically operate under the assumption of precise and complete data, but real-world applications often involve noisy, incomplete, or ambiguous information. Neutrosophic sets extend fuzzy logic by incorporating three components: truth, indeterminacy, and falsity, allowing for a more nuanced representation of uncertain data. This paper explores the theoretical foundations of neutrosophic sets and their integration with neural networks, highlighting the challenges in computational complexity, training, and optimization. The paper also discusses the potential applications of neutrosophic neural networks …

Emergent Operator Logic: A Foundational Framework For Dynamic Reasoning And Generative Intelligence, Mona Gharib, Abduallah Gamal, Muhammad Nawaz, Basma Nasir

Neutrosophic Systems with Applications

This paper introduces Emergent Operator Logic (EOL), a framework that treats propositions as continuous operators $F_p:X \rightarrow X$ on a complete metric state space $( X,d )$ and evaluates truth after action via a continuous valuation $V:X \rightarrow [ 0,1 ]$. Logical composition is realized by three operator-level connectives: sequential $p \circ q$(causal order), parallel $p\parallel q$(1-Lipschitz cooperative blend), and the emergent synthesis $E( p,q ) = \frac12( F_p \circ F_q + F_q \circ F_p )$, which symmetrizes non-commuting actions. We provide a Hilbert-style proof system (sound), an algebraic semantics via E-algebras, and show that the category of E-algebras is …