Computer Sciences Commons^™

Penforge: On-The-Fly Expert Agent Construction For Automated Penetration Testing, Huihui Huang, Jieke Shi, Junkai Chen, Ting Zhang, Yikun Li, Chengran Yang, Eng Lieh Ouh, Lwin Khin Shar, David Lo

Research Collection School Of Computing and Information Systems

Penetration testing is essential for identifying vulnerabilities in web applications before real adversaries can exploit them. Recent work has explored automating this process with Large Language Model (LLM)-powered agents, but existing approaches either rely on a single generic agent that struggles in complex scenarios or narrowly specialized agents that cannot adapt to diverse vulnerability types. We therefore introduce PenForge, a framework that dynamically constructs expert agents during testing rather than relying on those prepared beforehand. By integrating automated reconnaissance of potential attack surfaces with agents instantiated on the fly for context-aware exploitation, PenForge achieves a 30.0% exploit success rate (12/40) …

Stacked From One: Multi-Scale Self-Injection For Context Window Extension, Wei Han, Pan Zhou, Shuicheng Yan

Research Collection School Of Computing and Information Systems

The limited context window of contemporary large language models (LLMs) remains a primary bottleneck for their broader application across diverse domains. Although continual pre-training on long-context data offers a straightforward solution, it incurs prohibitive data acquisition and computational costs. To address this challenge, we propose SHAREDLLM, a novel framework based on multi-grained context compression and query-aware information acquisition. SHAREDLLM comprises two stacked short-context LLMs: a lower model serving as a compressor and an upper model acting as a decoder. The lower model compresses long inputs into compact, multi-grained representations, which are then forwarded to the upper model for context-aware processing. …

Thinktank-Me: A Multi-Expert Framework For Middle East Event Forecasting, Haoxuan Li, He Chang, Yunshan Ma, Yi Bin, Yang Yang, See-Kiong Ng, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Event forecasting is inherently influenced by multifaceted considerations, including international relations, regional historical dynamics, and cultural contexts. However, existing LLM-based approaches employ single-model architectures that generate predictions along a singular explicit trajectory, constraining their ability to capture diverse geopolitical nuances across complex regional contexts. To address this limitation, we introduce ThinkTank-ME, a novel Think Tank framework for Middle East event forecasting that emulates collaborative expert analysis in real-world strategic decision-making. To facilitate expert specialization and rigorous evaluation, we construct POLECAT-FOR-ME, a Middle East–focused event forecasting benchmark. Experimental results demonstrate the superiority of multi-expert collaboration in handling complex temporal geopolitical forecasting …

From Spatial To Actions: Grounding Vision-Language-Action Model In Spatial Foundation Priors, Zhengshen Zhang, Hao Li, Yalun Dai, Zhengbang Zhu, Lei Zhou, Chenchen Liu, Dong Wang, Francis E. H. Tay, Sijin Chen, Ziwei Liu, Yuxiao Liu, Xinghang Li, Pan Zhou

Research Collection School Of Computing and Information Systems

Existing vision-language-action (VLA) models act in 3D real-world but are typically built on 2D encoders, leaving a spatial reasoning gap that limits generalization and adaptability. Recent 3D integration techniques for VLAs either require specialized sensors and transfer poorly across modalities, or inject weak cues that lack geometry and degrade vision-language alignment. In this work, we introduce FALCON (From Spatial to Action), a novel paradigm that injects rich 3D spatial tokens into the action head. FALCON leverages spatial foundation models to deliver strong geometric priors from RGB alone, and includes an Embodied Spatial Model that can optionally fuse depth, or pose …

Match-A-Fit, Adan Diaz De Leon, Juan Marco Saca Dada, Brianna Mendoza, Arsalan Kataneh, Theophile Nsabimana, Pedro Jacobo

Presentations - 2026

Welcome to Match-a-Fit! Match-a-Fit is an iOS application that allows the user to create a digital closet by uploading images of their clothing items. With AI, the program can generate outfits based on the digital closet, the time, and the occasion. Match-a-Fit’s purpose is designed to help users who struggle to get ready, run out of time, or can’t decide on an outfit, by easily generating outfit options based on the occasion.

Comparative Analysis Of Mlp And Cnn Models For Cardiac Arrhythmia Classification, Veltman Okey-Ejowhor, Vahid Emamian

Posters - 2026

Electrocardiogram (ECG) is a record of the electric activity of the heart over time. ECG analysis plays a pivotal role in diagnosing critical heart conditions. Significant developments have been made in the realm of deep learning and applied artificial intelligence. These deep learning models have been utilized heavily because of their ability to analyze deep morphological features of each signal. The model architecture used in this study is a convolutional neural network (CNN) combined with a multi-layered perceptron (MLP). The MLP acts as an input filter that classifies normal heartbeat signals from abnormal. The CNN is the second filter in …

Using Ai-Based Predictive Scheduling To Improve Patient Flow And Reduce Wait Times In Healthcare Clinics, Oscar Martinez

Posters - 2026

• Healthcare systems face increasing challenges in patient access and wait times
• Average wait times for specialist care continue to rise, creating:
  • Delays in treatment
  • Reduced patient satisfaction
  • Increased system inefficiencies (Sanford, 2025)
• A major contributor is operational bottlenecks, defined as:
  • Points of congestion that slow or disrupt service flow
• Hospitals typically operate under process layouts, which:
  • Handle diverse patient needs
  • Reduce specialization efficiency
• Contributing factors to bottlenecks:
  • Physician shortages and burnout
  • Administrative burden
  • Inefficient scheduling systems (Moura & Pinho, 2025)
• AI offers potential solutions through:
  • Predictive scheduling
  • Automation of administrative processes
  • Data-driven optimization of patient flow

Optimizing Retail Grocery Inventory Using Ai And Large Language Models: Evidence On Forecast Accuracy, Waste Reduction, And Cost Efficiency, Robert Miller, Stephen Garcia, Brandon Ermis

Posters - 2026

Aim: To evaluate how AI and LLMs improve forecasting accuracy, reduce waste, and enhance inventory decision-making

Beyond Technology Acceptance: Ai Adoption In The United States And Korean Accounting Firms, Madeline Ortega, Brenda Vazquez Saavedra

Posters - 2026

A comparison of AI adoption between the United States and South Korea

Think First, Chatgpt Later: Guiding Human-Ai Collaboration For Learning Gains In Independent Human Creativity, Sarah Shi Hui Wong, Sophia Xuefei Qiu

Research Collection School of Social Sciences

Generative artificial intelligence (AI) tools such as ChatGPT can boost creative performance, but do these boosts translate into learning gains? This study examined whether the benefits of ChatGPT for creativity persist even when its assistance is removed, and how people can effectively use ChatGPT to enhance their learning and independent creativity. University students (N = 196) solved a creative product improvement task either independently (human-only group) or using ChatGPT freely (general-AI group) or using ChatGPT in a guided way (regulated-AI group). Specifically, the regulated-AI group used a novel “think first, ChatGPT later” approach—they first generated their own ideas, then collaborated …

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 …

Semat: Semantic Enhanced Natural Image Interactive Matting, Ruihao Xia, Yu Liang, Peng-Tao Jiang, Hao Zhang, Qianru Sun, Yang Tang, Bo Li, Pan Zhou

Research Collection School Of Computing and Information Systems

Recent approaches attempt to adapt powerful interactive segmentation models, such as SAM, to interactive matting and fine-tune the models based on synthetic matting datasets. However, models trained on synthetic data fail to generalize to complex and occlusion scenes. We address this challenge by proposing a new matting dataset based on the COCO dataset, namely COCO-Matting. It selects real-world complex images from COCO and converts semantic segmentation masks to matting labels. The built COCO-Matting comprises an extensive collection of 36,980 human instance-level alpha mattes in complex natural scenarios. Furthermore, existing SAM-based matting methods extract intermediate features and masks from a frozen …

Distributional Vision-Language Alignment By Cauchy-Schwarz Divergence, Wenzhe Yin, Zehao Xiao, Pan Zhou, Shujian Yu, Jiayi Shen, Jan-Jakob Sonke, Stratis Gavves

Research Collection School Of Computing and Information Systems

Vision-language alignment is crucial for various downstream tasks such as cross-modal generation and retrieval. Previous multimodal approaches like CLIP utilize InfoNCE to maximize mutual information, primarily aligning pairwise samples across modalities while overlooking distributional differences. In addition, InfoNCE has inherent conflict in terms of alignment and uniformity in multimodality, leading to suboptimal alignment with modality gaps. To overcome the limitations, we propose CS-Aligner, a novel framework that performs distributional vision-language alignment by integrating Cauchy-Schwarz (CS) divergence with mutual information. CS-Aligner captures both the global distribution information of each modality and the pairwise semantic relationships. We find that the CS divergence …

Bridging Draft Policy Misalignment: Group Tree Optimization For Speculative Decoding, Shijing Hu, Jingyang Li, Zhihui Lu, Pan Zhou

Research Collection School Of Computing and Information Systems

Speculative decoding accelerates large language model (LLM) inference by letting a lightweight draft model propose multiple tokens that the target model verifies in parallel. Yet existing training objectives optimize only a single greedy draft path, while decoding follows a tree policy that re-ranks and verifies multiple branches. This draft policy misalignment limits achievable speedups. We introduce Group Tree Optimization (GTO), which aligns training with the decoding-time tree policy through two components: (i) Draft Tree Reward, a sampling-free objective equal to the expected acceptance length of the draft tree under the target model, directly measuring decoding performance; (ii) Group-based Draft Policy …

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 …

Propaganda Ai: An Analysis Of Semantic Divergence In Large Language Models, Nay Myat Min, Long H. Pham, Yige Li, Jun Sun

Research Collection School Of Computing and Information Systems

Large language models (LLMs) can exhibit concept-conditioned semantic divergence: common high-level cues (e.g., ideologies, public figures) elicit unusually uniform, stance-like responses that evade token-trigger audits. This behavior falls in a blind spot of current safety evaluations, yet carries major societal stakes, as such concept cues can steer content exposure at scale. We formalize this phenomenon and present RAVEN (Response Anomaly Vigilance), a black-box audit that flags cases where a model is simultaneously highly certain and atypical among peers by coupling semantic entropy over paraphrastic samples with cross-model disagreement. In a controlled LoRA fine-tuning study, we implant a concept-conditioned stance using …

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 …

Who You Explain To Matters: Learning By Explaining To Conversational Agents With Different Pedagogical Roles, Zhengtao Xu, Junti Zhang, Anthony Tang, Yi-Chieh Lee

Research Collection School Of Computing and Information Systems

Conversational agents are increasingly used in education for learning support. An application is “learning by explaining”, where learners explain their understanding to an agent. However, existing research focuses on single roles, leaving it unclear how different pedagogical roles influence learners’ interaction patterns, learning outcomes and experiences. We conducted a between-subjects study (N=96) comparing agents with three pedagogical roles (Tutee, Peer, Challenger) and a control condition while learning an economics concept. We found that different pedagogical roles shaped learning dynamics, including interaction patterns and experiences. Specifically, the Tutee agent elicited the most cognitive investment but led to high pressure. The Peer …

Reasoning On Time-Series For Financial Technical Analysis, Kelvin J. L. Koa, Jan Chen, Yunshan Ma, Huanhuan Zheng, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

While Large Language Models have been used to produce interpretable stock forecasts, they mainly focus on analyzing textual reports but not historical price data, also known as Technical Analysis. This task is challenging as it switches between domains: the stock price inputs and outputs lie in the time-series domain, while the reasoning step should be in natural language. In this work, we introduce Verbal Technical Analysis (VTA), a novel framework that combine verbal and latent reasoning to produce stock time-series forecasts that are both accurate and interpretable. To reason over time-series, we convert stock price data into textual annotations 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 …

Generative Artificial Intelligence With A Human Touch: Building Hana, Conrad Johnson

Faculty Scholarship

This Essay examines how generative artificial intelligence (GenAI) can be integrated into legal education and public interest law practice in a way that meaningfully enhances — rather than diminishes — human judgment, professional responsibility, and access to justice. Drawing on the experience of Columbia Law School’s Lawyering in the Digital Age Clinic, the Essay situates GenAI within an experiential pedagogy that emphasizes competence, ethical awareness, and collaborative problem-solving. It argues that law students and lawyers must move beyond a passive or uncritical use of GenAI tools; toward a deeper understanding of how these systems operate, the risks they pose, and …

Learning Techniques In Prediction Of Functional Epigenomic Events, Mohammad Shiri

Computer Science Theses & Dissertations

Accurately predicting functional epigenomic events from DNA sequences is critical to understanding gene regulation and the functional impact of non-coding variants. Despite considerable progress, critical challenges hamper the effectiveness and efficiency of existing deep learning approaches. These challenges include negative transfer in multi-task learning (MTL), suboptimal network architectures, and pervasive label noise, particularly the positive-unlabeled problem arising from data sparsity in single-cell assays. This dissertation presents a cohesive framework of novel learning techniques to effectively address these challenges. First, a highly scalable task grouping framework is presented to mitigate negative transfer in deep MTL. This method clusters tasks based on …

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 …

A General Weighting Theory For Ensemble Learning: Beyond Variance Reduction Via Spectral And Geometric Structure, Ernest Fokoue

Articles

Ensemble learning is traditionally justified as a variance-reduction strategy, explaining its strong performance for unstable predictors such as decision trees. This explanation, however, does not account for ensembles constructed from intrinsically stable estimators-including smoothing splines, kernel ridge regression, Gaussian process regression, and other regularized reproducing kernel Hilbert space (RKHS) methods whose variance is already tightly controlled by regularization and spectral shrinkage. This paper develops a general weighting theory for ensemble learning that moves beyond classical variance-reduction arguments. We formalize ensembles as linear operators acting on a hypothesis space and endow the space of weighting sequences with geometric and spectral constraints. …

Development Of Deep Fused Neural Architecture For Ancient Tamil Palm-Leaf Manuscript Recognition, Hariharan P Mr

Theses and Dissertations

Digitizing Tamil palm-leaf manuscripts is important for education, communication, and the preservation of cultural heritage. The complex structure of the Tamil script, the wide range of handwriting styles, and the degradation seen in ancient Tamil palm-leaf manuscripts make these texts very difficult to read and understand. Digital Image Processing (DIP), document analysis techniques, and traditional Optical Character Recognition (OCR) are unable to handle noise, background interference, faded ink, and limited labelled data, motivating the need for robust, effective Deep Learning (DL)- based solutions.

As a prerequisite to understanding and designing effective recognition systems for ancient manuscripts, this thesis first examines …

Ai Adoption In Research Administration At Emerging Research Institutions, Dylan Ruediger, Ruby Macdougall, Stefanie Brachfield, Douglas R. Dechow, Jonathan Parker, Jana Remy

Library Articles and Research

"With funding from the National Science Foundation’s GRANTED program (grant #2437518), Ithaka S+R, Chapman University, and Montclair State University organized two workshops to help research administrators consider how to leverage AI to build research capacity at ERIs. Our first workshop, held at Montclair State in September 2025, brought together 31 participants from 13 academic and medical institutions in the New York/New Jersey/Pennsylvania region. Our second workshop, hosted by Chapman University on December 5, 2025, included 32 participants from 13 colleges and universities in Southern California. The approximately 2,600 ERIs in the United States receive a disproportionately small amount of federal …

The Core-Modulation Architecture (Cma): A Structural Overview Of A 14-Paper Research Program (Preprint), Griselda Poe

Publications and Research

This document provides a structural overview of the Core-Modulation Architecture (CMA), a 14-paper research program on cognition, communication, and AI interaction.

The series specifies the conditions under which cognition operates, terminates, fails, and generates structure. Rather than describing cognition by its contents (beliefs, emotions, decisions), it defines cognition through its underlying architecture: constraint-governed processing across layers with distinct termination conditions.

The framework introduces a layered model consisting of Core processing (constraint preservation and structural coherence) and Modulation (affective calibration and social interface adjustment), extended by a Prior layer as the source of constraints. Across the series, phenomena such as miscommunication, …

Classification Of Land Cover In Sentinel-2 Imagery Using Machine Learning Models, Ehsan Ali Al-Zubaidi, Mohammed Ridha Hammoodi, Ahmed Naser Alzurfi

Al-Bahir

Remote sensing data of medium resolution are commonly used to classify land cover, and machine learning (ML) models have taken on a central aspect in the necessary data analysis. Ordinarily, land cover is coded on a pixel basis on the basis of Digital Number (DN) values, which in turn are computed across several spectral bands. This paper is concerned with land cover mapping in Mosul, Iraq, based on satellite images captured by Sentinel-2. Two platforms featuring unsupervised classification algorithms were used, Google Earth Engine and ArcMap, making it possible to use K-means and X-means in Google Earth Engine and ISO …

When Ai Writes The Doctoral Thesis: Reclaiming The Oral Defence As A Learning Development Intervention, Valerie A. Storey

All Faculty and Staff Scholarship

Large language models have fundamentally challenged traditional methods of verifying doctoral competency as AI-generated text becomes increasingly difficult to distinguish from human scholarship. This paper argues that thesis committees and doctoral supervisors must reclaim the oral defence as a critical checkpoint for assessing authentic threshold crossing rather than a ceremonial rite of passage. Drawing on historical examples from medieval oral disputations through to the rise of written theses, this paper asserts the necessity of returning to rigorous oral assessment. Given the limitations of detection technologies and the growing use of AI in thesis writing, oral defences must move from confirmatory …