Digital Commons Network^™

Can Federated Learning Solve Ai’S Data Privacy Problem?: A Legal Analysis, Warren B. Chik, Florian Gamper

Research Collection Yong Pung How School Of Law

Federated learning (FL) is a method of training AI systems on different datasets without sharing data. The promise of FL is to enable AI systems to be trained on data, including personal data, while preserving data privacy and confidentiality, and thus, inter alia, facilitate compliance with data protection legislation. FL has generated a considerable interest amongst the computer science community, yet there is a dearth of legal analysis of FL. This is a problem because the question of whether FL facilitates compliance with data protection legislation is a legal question. This article will fill this lacuna by providing a comprehensive …

Constrained Assortment Optimization Under The Cross-Nested Logit Model, Cuong Le, Tien Mai

Research Collection School Of Computing and Information Systems

We study the assortment optimization problem under general linear constraints, where the customer choice behavior is captured by the cross-nested logit model. In this problem, there is a set of products organized into multiple subsets (or nests), where each product can belong to more than one nest. The aim is to find an assortment to offer to customers so that the expected revenue is maximized. We show that, under the cross-nested logit model, the unconstrained assortment problem is NP-hard even when there are only two nests, and the problem is generally NP-hard to approximate to any constant factors. To tackle …

Video Editing For Video Retrieval, Bin Zhu, Kevin Flanagan, Adriano Fragomeni, Michael Wray, Dima Damen

Research Collection School Of Computing and Information Systems

Though pre-training vision-language models have demonstrated significant benefits in boosting video-text retrieval performance from large-scale web videos, fine-tuning still plays a critical role with manually annotated clips with start and end times, which requires considerable human effort. To address this issue, we explore an alternative cheaper source of annotations, single timestamps, for video-text retrieval. We initialise clips from timestamps in a heuristic way to warm up a retrieval model. Then a video clip editing method is proposed to refine the initial rough boundaries to improve retrieval performance. A student-teacher network is introduced for video clip editing: the teacher model is …

Stagedvulbert: Multi-Granular Vulnerability Detection With A Novel Pre-Trained Code Model, Yuan Jiang, Yujian Zhang, Xiaohong Su, Christoph Treude, Tiantian Wang

Research Collection School Of Computing and Information Systems

The emergence of pre-trained model-based vulnerability detection methods has significantly advanced the field of automated vulnerability detection. However, these methods still face several challenges, such as difficulty in learning effective feature representations of statements for fine-grained predictions and struggling to process overly long code sequences. To address these issues, this study introduces StagedVulBERT, a novel vulnerability detection framework that leverages a pre-trained code language model and employs a coarse-to-fine strategy. The key innovation and contribution of our research lies in the development of the CodeBERT-HLS component within our framework, specialized in hierarchical, layered, and semantic encoding. This component is designed …

Nigerian Software Engineer Or American Data Scientist? Github Profile Recruitment Bias In Large Language Models, Takashi Nakano, Kazumasa Shimari, Raula Gaikovina Kula, Christoph Treude, Marc Cheong, Kenichi Matsumoto

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have taken the world by storm, demonstrating their ability not only to automate tedious tasks, but also to show some degree of proficiency in completing software engineering tasks. A key concern with LLMs is their “black-box” nature, which obscures their internal workings and could lead to societal biases in their outputs. In the software engineering context, in this early results paper, we empirically explore how well LLMs can automate recruitment tasks for a geographically diverse software team. We use OpenAI's ChatGPT to conduct an initial set of experiments using GitHub User Profiles from four regions to …

Predicting The Limits: Tailoring Unnoticeable Hand Redirection Offsets In Virtual Reality To Individuals' Perceptual Boundaries, Martin Feick, Kora Persephone Regitz, Lukas Gehrke, André Zenner, Anthony Tang, Tobias Patrick Jungbluth, Maurice Rekrut, Antonio Krüger

Research Collection School Of Computing and Information Systems

Many illusion and interaction techniques in Virtual Reality (VR) rely on Hand Redirection (HR), which has proved to be effective as long as the introduced offsets between the position of the real and virtual hand do not noticeably disturb the user experience. Yet calibrating HR offsets is a tedious and time-consuming process involving psychophysical experimentation, and the resulting thresholds are known to be affected by many variables—limiting HR’s practical utility. As a result, there is a clear need for alternative methods that allow tailoring HR to the perceptual boundaries of individual users. We conducted an experiment with 18 participants combining …

Joint Weakly Supervised Image Emotion Analysis Based On Interclass Discrimination And Intraclass Correlation, Xinyue Zhang, Zhaoxia Wang, Guitao Cao, Seng-Beng Ho

Research Collection School Of Computing and Information Systems

Regional information-based image emotion analysis has recently garnered significant attention. However, existing methods often focus on identifying region proposals through layered steps or merely rely on visual saliency. These approaches may lead to an underestimation of emotional categories and a lack of comprehensive interclass discrimination perception and emotional intraclass contextual mining. To address these limitations, we propose a novel approach named InterIntraIEA, which combines interclass discrimination and intraclass correlation joint learning capabilities for image emotion analysis. The proposed method not only employs category-specific dictionary learning for class adaptation, but also models intraclass contextual relationships and perceives correlations at the channel …

Navigating Governance Paradigms: A Cross-Regional Comparative Study Of Generative Ai Governance Processes & Principle, Jose Luna, Ivan Tan, Xiaofei Xie, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

As Generative Artificial Intelligence (GenAI) technologies evolve at an unprecedented rate, global governance approaches struggle to keep pace with the technology, highlighting a critical issue in the governance adaptation of significant challenges. Depicting the nuances of nascent and diverse governance approaches based on risks, rules, outcomes, principles, or a mix across different regions around the globe is fundamental to discern discrepancies and convergences and to shed light on specific limitations that need to be addressed, thereby facilitating the safe and trustworthy adoption of GenAI. In response to the need and the evolving nature of GenAI, this paper seeks to provide …

Exploring Conversations Between A Practitioner And A Person With Dementia, Kotaro Hara, Rosiana Natalie, Wei Soon Cheong, Jingjing Gu, Qianli Xu

Research Collection School Of Computing and Information Systems

In social service centers, practitioners engage in conversations with clients with dementia to facilitate their daily activities and provide support when they are distressed. However, the nature of the care demands the practitioner’s active engagement, which becomes difficult to deliver as the number of people who need care expands. Researchers have been investigating the efficacy of developing agents that assume conversational tasks to alleviate this work. To contribute to the future design of agents for caregiving, we collected and analyzed ten conversations between clients with mild dementia and practitioners who provide care. Our analyses of turn-taking dynamics and dialogue acts …

Temporal Relational Graph Convolutional Network Approach To Financial Performance Prediction, Jeyaraman Brindha Priyadarshini, Bing Tian Dai, Yuan Fang

Research Collection School Of Computing and Information Systems

Accurately predicting financial entity performance remains a challenge due to the dynamic nature of financial markets and vast unstructured textual data. Financial knowledge graphs (FKGs) offer a structured representation for tackling this problem by representing complex financial relationships and concepts. However, constructing a comprehensive and accurate financial knowledge graph that captures the temporal dynamics of financial entities is non-trivial. We introduce FintechKG, a comprehensive financial knowledge graph developed through a three-dimensional information extraction process that incorporates commercial entities and temporal dimensions and uses a financial concept taxonomy that ensures financial domain entity and relationship extraction. We propose a temporal and …

Self-Adaptive Fine-Grained Multi-Modal Data Augmentation For Semi-Supervised Muti-Modal Coreference Resolution, Li Zheng, Boyu Chen, Hao Fei, Fei Li, Shengqiong Wu, Lizi Liao, Donghong Ji

Research Collection School Of Computing and Information Systems

Coreference resolution, an essential task in natural language processing, is particularly challenging in multi-modal scenarios where data comes in various forms and modalities. Despite advancements, limitations due to scarce labeled data and underleveraged unlabeled data persist. We address these issues with a self-adaptive fine-grained multi-modal data augmentation framework for semi-supervised MCR, focusing on enriching training data from labeled datasets and tapping into the untapped potential of unlabeled data. Regarding the former issue, we first leverage text coreference resolution datasets and diffusion models,to perform fine-grained text-to-image generation with aligned text entities and image bounding boxes. We then introduce a self-adaptive selection …

An Empirical Study To Evaluate Aigc Detectors On Code Content, Jian Wang, Shangqing Liu, Xiaofei Xie, Yi Li

Research Collection School Of Computing and Information Systems

Artificial Intelligence Generated Content (AIGC) has garnered considerable attention for its impressive performance, with Large Language Models (LLMs), like ChatGPT, emerging as a leading AIGC model that produces high-quality responses across various applications, including software development and maintenance. Despite its potential, the misuse of LLMs, especially in security and safetycritical domains, such as academic integrity and answering questions on Stack Overflow, poses significant concerns. Numerous AIGC detectors have been developed and evaluated on natural language data. However, their performance on code-related content generated by LLMs remains unexplored. To fill this gap, in this paper, we present an empirical study evaluating …

Enhancing Recipe Retrieval With Foundation Models: A Data Augmentation Perspective, Fangzhou Song, Bin Zhu, Yanbin Hao, Shuo Wang

Research Collection School Of Computing and Information Systems

Learning recipe and food image representation in common embedding space is non-trivial but crucial for cross-modal recipe retrieval. In this paper, we propose a new perspective for this problem by utilizing foundation models for data augmentation. Leveraging on the remarkable capabilities of foundation models (i.e., Llama2 and SAM), we propose to augment recipe and food image by extracting alignable information related to the counterpart. Specifically, Llama2 is employed to generate a textual description from the recipe, aiming to capture the visual cues of a food image, and SAM is used to produce image segments that correspond to key ingredients in …

Audio Description Customization, Rosiana Natalie, Ruei-Che Chang, Sheshadri Smitha, Anhong Guo, Kotaro Hara

Research Collection School Of Computing and Information Systems

Blind and low-vision (BLV) people use audio descriptions (ADs) to access videos. However, current ADs are unalterable by end users, thus are incapable of supporting BLV individuals’ potentially diverse needs and preferences. This research investigates if customizing AD could improve how BLV individuals consume videos. We conducted an interview study (Study 1) with fifteen BLV participants, which revealed desires for customizing properties like length, emphasis, speed, voice, format, tone, and language. At the same time, concerns like interruptions and increased interaction load due to customization emerged. To examine AD customization’s effectiveness and tradeoffs, we designed CustomAD, a prototype that enables …

Direct Range Proofs For Paillier Cryptosystem And Their Applications, Zhikang Xie, Mengling Liu, Haiyang Xue, Man Ho Au, Robert H. Deng, Siu-Ming Yiu

Research Collection School Of Computing and Information Systems

The Paillier cryptosystem is renowned for its applications in electronic voting, threshold ECDSA, multi-party computation, and more, largely due to its additive homomorphism. In these applications, range proofs for the Paillier cryptosystem are crucial for maintaining security, because of the mismatch between the message space in the Paillier system and the operation space in application scenarios. In this paper, we present novel range proofs for the Paillier cryptosystem, specifically aimed at optimizing those for both Paillier plaintext and affine operation. We interpret encryptions and affine operations as commitments over integers, as opposed to solely over ZN. Consequently, we propose direct …

Densetrack : Drone-Based Crowd Tracking Via Density-Aware Motion-Appearance Synergy, Yi Lei, Huilin Zhu, Jingling Yuan, Guangli Xiang, Xian Zhong, Shengfeng He

Research Collection School Of Computing and Information Systems

Drone-based crowd tracking faces difficulties in accurately identifying and monitoring objects from an aerial perspective, largely due to their small size and close proximity to each other, which complicates both localization and tracking. To address these challenges, we present the Density-aware Tracking (DenseTrack) framework. DenseTrack capitalizes on crowd counting to precisely determine object locations, blending visual and motion cues to improve the tracking of small-scale objects. It specifically addresses the problem of cross-frame motion to enhance tracking accuracy and dependability. DenseTrack employs crowd density estimates as anchors for exact object localization within video frames. These estimates are merged with motion …

Beat-It : Beat-Synchronized Multi-Condition 3d Dance Generation, Zikai Huang, Xuemiao Xu, Cheng Xu, Huaidong Zhang, Chenxi Zheng, Jing Qin, Shengfeng He

Research Collection School Of Computing and Information Systems

Dance, as an art form, fundamentally hinges on the precise synchronization with musical beats. However, achieving aesthetically pleasing dance sequences from music is challenging, with existing methods often falling short in controllability and beat alignment. To address these shortcomings, this paper introduces Beat-It, a novel framework for beat-specific, key pose-guided dance generation. Unlike prior approaches, Beat-It uniquely integrates explicit beat awareness and key pose guidance, effectively resolving two main issues: the misalignment of generated dance motions with musical beats, and the inability to map key poses to specific beats, critical for practical choreography. Our approach disentangles beat conditions from music …

Onerestore : A Universal Restoration Framework For Composite Degradation, Yu Guo, Yuan Gao, Yuxu Lu, Huilin Zhu, Ryan Wen Liu, Shengfeng He

Research Collection School Of Computing and Information Systems

In real-world scenarios, image impairments often manifest as composite degradations, presenting a complex interplay of elements such as low light, haze, rain, and snow. Despite this reality, existing restoration methods typically target isolated degradation types, thereby falling short in environments where multiple degrading factors coexist. To bridge this gap, our study proposes a versatile imaging model that consolidates four physical corruption paradigms to accurately represent complex, composite degradation scenarios. In this context, we propose OneRestore, a novel transformer-based framework designed for adaptive, controllable scene restoration. The proposed framework leverages a unique cross-attention mechanism, merging degraded scene descriptors with image features, …

Documenting Ethical Considerations In Open Source Ai Models, Haoyu Gao, Mansooreh Zahedi, Christoph Treude, Sarita Rosenstock, Marc Cheong

Research Collection School Of Computing and Information Systems

Background: The development of AI-enabled software heavily depends on AI model documentation, such as model cards, due to different domain expertise between software engineers and model developers. From an ethical standpoint, AI model documentation conveys critical information on ethical considerations along with mitigation strategies for downstream developers to ensure the delivery of ethically compliant software. However, knowledge on such documentation practice remains scarce. Aims: The objective of our study is to investigate how developers document ethical aspects of open source AI models in practice, aiming at providing recommendations for future documentation endeavours. Method: We selected three sources of documentation on …

An Empirical Study Of Api Misuses Of Data-Centric Libraries, Akalanda Galappaththi, Sarah Nadi, Christoph Treude

Research Collection School Of Computing and Information Systems

Developers rely on third-party library Application Programming Interfaces (APIs) when developing software. However, libraries typically come with assumptions and API usage constraints, whose violation results in API misuse. API misuses may result in crashes or incorrect behavior. Even though API misuse is a well-studied area, a recent study of API misuse of deep learning libraries showed that the nature of these misuses and their symptoms are different from misuses of traditional libraries, and as a result highlighted potential shortcomings of current misuse detection tools. We speculate that these observations may not be limited to deep learning API misuses but may …

A Survey Of Protocol Fuzzing, Xiaohan Zhang, Cen Zhang, Xinghua Li, Zhengjie Du, Bing Mao, Yeting Li, Pan Li

Research Collection School Of Computing and Information Systems

Communication protocols form the bedrock of our interconnected world, yet vulnerabilities within their implementations pose significant security threats. Recent developments have seen a surge in fuzzing-based research dedicated to uncovering these vulnerabilities within protocol implementations. However, there still lacks a systematic overview of protocol fuzzing for answering the essential questions such as what the unique challenges are, how existing works solve them, and so on. To bridge this gap, we conducted a comprehensive investigation of related works from both academia and industry. Our study includes a detailed summary of the specific challenges in protocol fuzzing and provides a systematic categorization …

An Empirical Study Of Automatic Program Repair Techniques For Injection Vulnerabilities, Tingwei Zhu, Tongtong Xu, Kui Liu, Jiayuan Zhou, Xing Hu, Xin Xia, Tian Zhang, David Lo

Research Collection School Of Computing and Information Systems

Injection vulnerabilities are among the most serious and dangerous security defects, as they can be exploited by attackers to inject malicious inputs and carry out cybercrimes. Timely fixing of injection vulnerabilities is crucial. However, manual repairs of injection vulnerabilities often require specialized knowledge and are prone to errors, posing a challenge and a heavy burden on developers. In recent years, Automated Program Repair (APR) techniques have shown promising momentum in automatically fixing general defects. Yet, there has been no research on how APR techniques perform in repairing injection vulnerabilities. Therefore, in this paper, we conduct an empirical study. We first …

Refinement Of Alphafold-Predicted Models Using Cryo-Em Density Maps And Enhancement Of Protein Secondary Structure Topologies With Residue Contacts, Maytha Naif Alshammari

Computer Science Theses & Dissertations

Proteins play an important role in almost every biological process. Understanding the mechanism of protein function requires knowledge of three-dimensional (3D) structures. Traditionally, the determination of 3D structures has presented significant challenges. However, Cryo-Electron Microscopy (Cryo-EM) has revolutionized the field of structural biology, providing a powerful technique for atomic structure determination. This dissertation delves into the potential of cryoEM in two ways. First, this dissertation presents a new flexible fitting approach, utilizing Normal Mode Analysis (NMA) and Elastic Network Models (ENMs) to refine AlphaFold-predicted models by optimizing the structures to match cryo-EM density maps. This approach identifies the optimal mode …

Demystifying And Extracting Fault-Indicating Information From Logs For Failure Diagnosis, Junjie Huang, Zhihan Jiang, Jinyang Liu, Yintong Huo, Jiazhen Gu, Zhuangbin Chen, Cong Feng, Hui Dong, Zengyin Yang, Michael R. Lyu

Research Collection School Of Computing and Information Systems

Logs are imperative in the maintenance of online service systems, which often encompass important information for effective failure mitigation. While existing anomaly detection methodologies facilitate the identification of anomalous logs within extensive runtime data, manual investigation of log messages by engineers remains essential to comprehend faults, which is labor-intensive and error-prone. Upon examining the log-based troubleshooting practices at CloudA 1, we find that engineers typically prioritize two categories of log information for diagnosis. These include fault-indicating descriptions, which record abnormal system events, and fault-indicating parameters, which specify the associated entities. Motivated by this finding, we propose an approach to automatically …

Privacy Risks And Regulatory Challenges In Smart Grids And Renewable Energy Systems, Mikołaj Rajca

internetowy Kwartalnik Antymonopolowy i Regulacyjny (internet Quarterly on Antitrust and Regulation)

Smart grid technologies are central to the global shift towards a more efficient and sustainable energy infrastructure, integrating advanced digital systems with traditional power networks. While these technologies offer significant benefits, including enhanced energy management and the seamless integration of renewable energy sources, they also introduce complex privacy challenges. The extensive data collection and real-time communication capabilities inherent in smart grids raise concerns over consumer privacy, data breaches, and cybersecurity threats. This paper critically examines these privacy risks within the context of evolving regulatory frameworks such as the GDPR, NIS2 Directive, and the forthcoming EU AI Act. The discussion emphasizes …

Robust And Generalizable Representations In The Hippocampus, Hung-Tu Chen

Dartmouth College Ph.D Dissertations

An intelligent system must balance generalizing across similar experiences with maintaining the distinctiveness of each experience. This thesis explores how the hippocampus manages this balance through its neural representations to support adaptive behavior. In Chapter 1, I provide an overview of key hippocampal phenomena that contribute to this process, including remapping, splitter signal, and replay. In Chapter 2, I challenge the concept of random remapping by showing that it is possible to predict, better than chance, how a given experience will be encoded in the hippocampus across different subjects. This suggests that encoding of related experiences, which was previously thought …

A Framework For Human Evaluation Of Large Language Models In Healthcare Derived From Literature Review, Thomas Yu Chow Tam, Sonish Sivarajkumar, Sumit Kapoor, Alisa V Stolyar, Katelyn Polanska, Karleigh R Mccarthy, Hunter Osterhoudt, Xizhi Wu, Shyam Visweswaran, Sunyang Fu, Piyush Mathur, Giovanni E Cacciamani, Cong Sun, Yifan Peng, Yanshan Wang

Faculty, Staff and Student Publications

With generative artificial intelligence (GenAI), particularly large language models (LLMs), continuing to make inroads in healthcare, assessing LLMs with human evaluations is essential to assuring safety and effectiveness. This study reviews existing literature on human evaluation methodologies for LLMs in healthcare across various medical specialties and addresses factors such as evaluation dimensions, sample types and sizes, selection, and recruitment of evaluators, frameworks and metrics, evaluation process, and statistical analysis type. Our literature review of 142 studies shows gaps in reliability, generalizability, and applicability of current human evaluation practices. To overcome such significant obstacles to healthcare LLM developments and deployments, we …

Architecting Standards: Leveraging Ia To Drive Emerging Technology Standards​, Noreen Y. Whysel

Publications and Research

In this talk for the annual meeting of the W3C Information Architecture Community Group, I discuss how standards bodies can learn from the Information Architecture field to improve accessibility and usability. By adopting user-centered design principles and engaging in iterative feedback loops, standards organizations can create more relevant and practical standards that align with real-world applications. Emphasizing collaboration with industry experts and end-users will help ensure that standards evolve along with technological advancements.

In the meantime, key standards are examined, such as ISO 9241, which provides guidelines for usability and user-centered design, and the W3C's Web Content Accessibility Guidelines (WCAG), …

Prompt And Accurate Grb Source Localization Aboard The Advanced Particle Astrophysics Telescope (Apt) And Its Antarctic Demonstrator (Adapt), Ye Htet, Marion Sudvarg, Jeremy Buhler, Roger Chamberlain, Wenlei Chen, James Buckley, Roger D. Chamberlain, Corrado Altomare, Matthew Andrew, Blake Bal, Richard G. Bose, Dana Braun, Eric Burns, Michael L. Cherry, Leonardo Di Venere, Jeffrey Dumonthier, Manel Errando, Stefan Funk

Computer Science Faculty Research & Creative Works

We characterize the performance of our computational pipeline for real-time gamma-ray burst (GRB) detection and localization aboard the Advanced Particle-astrophysics Telescope (APT) – a space-based observatory for MeV to TeV gamma-ray astronomy – and its smaller, balloon-borne prototype, the Antarctic Demonstrator for APT (ADAPT), whose scientific focus will be the detection of MeV transients. These instruments observe scintillation light from multiple Compton scattering and photoabsorption of gamma-ray photons across a series of CsI detector layers. We infer the incident angle of each photon's first scattering to localize its source direction to a Compton ring about the vector defined by its …

Exploring Saliency Bias In Manipulation Detection, Joshua Krinsky, Alan Bettis, Qiuyu Tang, Daniel Moreira, Aparna Bharati

Computer Science: Faculty Publications and Other Works

The social media-fuelled explosion of fake news and misinformation supported by tampered images has led to growth in the development of models and datasets for image manipulation detection. However, existing detection methods mostly treat media objects in isolation, without considering the impact of specific manipulations on viewer perception. Forensic datasets are usually analyzed based on the manipulation operations and corresponding pixel-based masks, but not on the semantics of the manipulation, i.e., type of scene, objects, and viewers’ attention to scene content. The semantics of the manipulation play an important role in spreading misinformation through manipulated images. In an attempt to …