Computer Sciences Commons^™

Fdi : Attack Neural Code Generation Systems Through User Feedback Channel, Zhensu Sun, Xiaoning Du, Xiapu Luo, Fu Song, David Lo, Li Li

Research Collection School Of Computing and Information Systems

Neural code generation systems have recently attracted increasing attention to improve developer productivity and speed up software development. Typically, these systems maintain a pre-trained neural model and make it available to general users as a service (e.g., through remote APIs) and incorporate a feedback mechanism to extensively collect and utilize the users' reaction to the generated code, i.e., user feedback. However, the security implications of such feedback have not yet been explored. With a systematic study of current feedback mechanisms, we find that feedback makes these systems vulnerable to feedback data injection (FDI) attacks. We discuss the methodology of FDI …

Developer Reactions To Protestware In Open Source Software: The Cases Of Color.Js And Es5.Ext, Youmei Fan, Dong Wang, Supatsara Wattanakriengkrai, Hathaichanok Damrongsiri, Christoph Treude, Hideaki Hata, Raula Gaikovina Kula

Research Collection School Of Computing and Information Systems

There is growing concern about maintainers self-sabotaging their work in order to take political or economic stances, a practice referred to as “protestware”. Our objective is to understand the discourse around discussions on such an attack, how it is received by the community, and whether developers respond to the attack in a timely manner. We study two notable protestware cases i.e., colors.js and es5-ext. Results indicate that protestware discussions are spread more quickly on the GitHub platform, while security vulnerabilities are faster on social media. By establishing a taxonomy of protestware discussions, we identify posts that express stances and provide …

An Empirical Study Of Static Analysis Tools For Secure Code Review, Wachiraphan Charoenwet, Patanamon Thongtanunam, Van-Thuan Pham, Christoph Treude

Research Collection School Of Computing and Information Systems

Early identification of security issues in software development is vital to minimize their unanticipated impacts. Code review is a widely used manual analysis method that aims to uncover security issues along with other coding issues in software projects. While some studies suggest that automated static application security testing tools (SASTs) could enhance security issue identification, there is limited understanding of SAST’s practical effectiveness in supporting secure code review. Moreover, most SAST studies rely on synthetic or fully vulnerable versions of the subject program, which may not accurately represent real-world code changes in the code review process. To address this gap, …

Aligning Human And Computational Coherence Evaluations, Jia Peng Lim, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Automated coherence metrics constitute an efficient and popular way to evaluate topic models. Previous work presents a mixed picture of their presumed correlation with human judgment. This work proposes a novel sampling approach to mining topic representations at a large scale while seeking to mitigate bias from sampling, enabling the investigation of widely used automated coherence metrics via large corpora. Additionally, this article proposes a novel user study design, an amalgamation of different proxy tasks, to derive a finer insight into the human decision-making processes. This design subsumes the purpose of simple rating and outlier-detection user studies. Similar to the …

Enhancing Multi-Agent System Testing With Diversity-Guided Exploration And Adaptive Critical State Exploitation, Xuyan Ma, Yawen Wang, Junjie Wang, Xiaofei Xie

Research Collection School Of Computing and Information Systems

Multi-agent systems (MASs) have achieved remarkable success in multi-robot control, intelligent transportation, and multiplayer games, etc. Thorough testing for MAS is urgently needed to ensure its robustness in the face of constantly changing and unexpected scenarios. Existing methods mainly focus on single-agent system testing and cannot be directly applied to MAS testing due to the complexity of MAS. To our best knowledge, there are fewer studies on MAS testing. While several studies have focused on adversarial attacks on MASs, they primarily target failure detection from an attack perspective, i.e., discovering failure scenarios, while ignoring the diversity of scenarios. In this …

Bugs In Pods: Understanding Bugs In Container Runtime Systems, Jiongchi Yu, Xiaofei Xie, Ceng Zhang, Sen Chen

Research Collection School Of Computing and Information Systems

Container Runtime Systems (CRSs), which form the foundational infrastructure of container clouds, are critically important due to their impact on the quality of container cloud implementations. However, a comprehensive understanding of the quality issues present in CRS implementations remains lacking. To bridge this gap, we conduct the first comprehensive empirical study of CRS bugs. Specifically, we gather 429 bugs from 8,271 commits across dominant CRS projects, including runc, gvisor, containerd, and cri-o. Through manual analysis, we develop taxonomies of CRS bug symptoms and root causes, comprising 16 and 13 categories, respectively. Furthermore, we evaluate the capability of popular testing approaches, …

Genixer : Empowering Multimodal Large Language Models As A Powerful Data Generator, Henry Hengyuan Zhao, Pan Zhou, Mike Zheng Shou

Research Collection School Of Computing and Information Systems

Multimodal Large Language Models (MLLMs) demonstrate exceptional problem-solving capabilities, but few research studies aim to gauge the ability to generate visual instruction tuning data. This paper proposes to explore the potential of empowering MLLMs to generate data independently without relying on GPT-4. We introduce Genixer, a comprehensive data generation pipeline consisting of four key steps: (i) instruction data collection, (ii) instruction template design, (iii) empowering MLLMs, and (iv) data generation and filtering. Additionally, we outline two modes of data generation: task-agnostic and task-specific, enabling controllable output. We demonstrate that a synthetic VQA-like dataset trained with LLaVA1.5 enhances performance on 10 …

Robust Image Classification System Via Cloud Computing, Aligned Multimodal Embeddings, Centroids And Neighbours, Wei Lun Koh, Boon Yong Koh, Bing Tian Dai

Research Collection School Of Computing and Information Systems

We propose a framework for a cloud-based application of an image classification system that is highly accessible, maintains data confidentiality, and robust to incorrect training labels. The end-to-end system is implemented using Amazon Web Services (AWS), with a detailed guide provided for replication, enhancing the ways which researchers can collaborate with a community of users for mutual benefits. A front-end web application allows users across the world to securely log in, contribute labelled training images conveniently via a drag-and-drop approach, and use that same application to query an up-to-date model that has knowledge of images from the community of users. …

Evaluating Szz Implementations : An Empirical Study On The Linux Kernel, Yunbo Lyu, Hong Jin Kang, Ratnadira Widyasari, Julia Lawall, David Lo

Research Collection School Of Computing and Information Systems

The SZZ algorithm is used to connect bug-fixing commits to the earlier commits that introduced bugs. This algorithm has many applications and many variants have been devised. However, there are some types of commits that cannot be traced by the SZZ algorithm, referred to as “ghost commits”. The evaluation of how these ghost commits impact the SZZ implementations remains limited. Moreover, these implementations have been evaluated on datasets created by software engineering researchers from information in bug trackers and version controlled histories. Since Oct 2013, the Linux kernel developers have started labelling bug-fixing patches with the commit identifiers of the …

Self-Supervised Spatial-Temporal Normality Learning For Time Series Anomaly Detection, Yutong Chen, Hongzuo Xu, Guansong Pang, Hezhe Qiao, Yuan Zhou, Mingsheng Shang

Research Collection School Of Computing and Information Systems

Time Series Anomaly Detection (TSAD) finds widespread applications across various domains such as financial markets, industrial production, and healthcare. Its primary objective is to learn the normal patterns of time series data, thereby identifying deviations in test samples. Most existing TSAD methods focus on modeling data from the temporal dimension, while ignoring the semantic information in the spatial dimension. To address this issue, we introduce a novel approach, called Spatial-Temporal Normality learning (STEN). STEN is composed of a sequence Order prediction-based Temporal Normality learning (OTN) module that captures the temporal correlations within sequences, and a Distance prediction-based Spatial Normality learning …

Neuron Sensitivity Guided Test Case Selection, Dong Huang, Qingwen Bu, Yichao Fu, Yuhao Qing, Xiaofei Xie, Junjie Chen, Heming Cui

Research Collection School Of Computing and Information Systems

Deep Neural Networks (DNNs) have been widely deployed in software to address various tasks (e.g., autonomous driving, medical diagnosis). However, they can also produce incorrect behaviors that result in financial losses and even threaten human safety. To reveal and repair incorrect behaviors in DNNs, developers often collect rich, unlabeled datasets from the natural world and label them to test DNN models. However, properly labeling a large number of datasets is a highly expensive and time-consuming task. To address the above-mentioned problem, we propose NSS, Neuron Sensitivity Guided Test Case Selection, which can reduce the labeling time by selecting valuable test …

Ai Coders Are Among Us : Rethinking Programming Language Grammar Towards Efficient Code Generation, Sun Zhensu, Du Xiaoning, Yang Zhou, Li Li, David Lo

Research Collection School Of Computing and Information Systems

Artificial Intelligence (AI) models have emerged as another important audience for programming languages alongside humans and machines, as we enter the era of large language models (LLMs). LLMs can now perform well in coding competitions and even write programs like developers to solve various tasks, including mathematical problems. However, the grammar and layout of current programs are designed to cater the needs of human developers -- with many grammar tokens and formatting tokens being used to make the code easier for humans to read. While this is helpful, such a design adds unnecessary computational work for LLMs, as each token …

Quantum Relaxation For Solving Multiple Knapsack Problems, Monit Sharma, Jin Yan, Hoong Chuin Lau, Rudy Raymond

Research Collection School Of Computing and Information Systems

Combinatorial problems are a common challenge in business, requiring finding optimal solutions under specified constraints. While significant progress has been made with variational approaches such as QAOA, most problems addressed are unconstrained (such as Max-Cut). In this study, we investigate a hybrid quantum-classical method for constrained optimization problems, particularly those with knapsack constraints that occur frequently in financial and supply chain applications. Our proposed method relies firstly on relaxations to local quantum Hamiltonians, defined through commutative maps. Drawing inspiration from quantum random access code (QRAC) concepts, particularly Quantum Random Access Optimizer (QRAO), we explore QRAO's potential in solving large constrained …

Ft2ra: A Fine-Tuning-Inspired Approach To Retrieval-Augmented Code Completion, Qi Guo, Shangqing Liu, Xiaofei Xie, Ze Tang Tang

Research Collection School Of Computing and Information Systems

The rise of code pre-trained models has significantly enhanced various coding tasks, such as code completion, and tools like GitHub Copilot. However, the substantial size of these models, especially large models, poses a significant challenge when it comes to fine-tuning them for specific downstream tasks. As an alternative approach, retrieval-based methods have emerged as a promising solution, augmenting model predictions without the need for fine-tuning. Despite their potential, a significant challenge is that the designs of these methods often rely on heuristics, leaving critical questions about what information should be stored or retrieved and how to interpolate such information for …

Efficient Cascaded Multiscale Adaptive Network For Image Restoration, Yichen Zhou, Pan Zhou, Teck Khim Ng

Research Collection School Of Computing and Information Systems

Image restoration, encompassing tasks such as deblurring, denoising, and super-resolution, remains a pivotal area in computer vision. However, efficiently addressing the spatially varying artifacts of various low-quality images with local adaptiveness and handling their degradations at different scales poses significant challenges. To efficiently tackle these issues, we propose the novel Efficient Cascaded Multiscale Adaptive (ECMA) Network. ECMA employs Local Adaptive Module, LAM, which dynamically adjusts convolution kernels across local image regions to efficiently handle varying artifacts. Thus, LAM addresses the local adaptiveness challenge more efficiently than costlier mechanisms like self-attention, due to its less computationally intensive convolutions. To construct a …

The Impact Of Data Recovery Criteria, Data Backup Schedule And Data Backup Prosses On The Efficiency Of Data Recovery Management In Data Centers, Maen T. Alrashdan, Mutaz Abdel Wahed, Emran Aljarrah, Mohammad Tubishat, Malek Alzaqebah, Nader Aljawarneh

All Works

A large-scale cloud data center must have a low failure incidence rate and great service dependability and availability. However, due to several issues, such as hardware and software malfunctions that regularly cause task and job failure, large-scale cloud data centers still have high failure rates. These mistakes can have a substantial impact on cloud service dependability and need a large resource allocation to recover from failures. Therefore, it is important to have an efficient management of data recovery to protect organizations data from loss. This paper aims to study some factors that may improve the management of data recovery by …

La Vida: Towards A Motivated Goal Reasoning Agent, Ursula Addison

Dissertations, Theses, and Capstone Projects

An autonomous agent deployed to operate over extended horizons in uncertain environments will encounter situations for which it was not designed. A class of these situations involves an invalidation of agent goals and limited guidance in establishing a new set of goals to pursue. An agent will benefit from some mechanism that will allow it to pursue new goals under these circumstances such that the goals are broadly useful in its environment and take advantage of its existing skills while aligning with societal norms. We propose augmenting a goal reasoning agent, i.e., an agent that can deliberate on and self-select …

Putting Gpt-4o To The Sword: A Comprehensive Evaluation Of Language, Vision, Speech, And Multimodal Proficiency, Sakib Shahriar, Brady D. Lund, Nishith Reddy Mannuru, Muhammad Arbab Arshad, Kadhim Hayawi, Ravi Varma Kumar Bevara, Aashrith Mannuru, Laiba Batool

All Works

As large language models (LLMs) continue to advance, evaluating their comprehensive capabilities becomes significant for their application in various fields. This research study comprehensively evaluates the language, vision, speech, and multimodal capabilities of GPT-4o. The study employs standardized exam questions, reasoning tasks, and translation assessments to assess the model’s language capability. Additionally, GPT-4o’s vision and speech capabilities are tested through image classification and object-recognition tasks, as well as accent classification. The multimodal evaluation assesses the model’s performance in integrating visual and linguistic data. Our findings reveal that GPT-4o demonstrates high accuracy and efficiency across multiple domains in language and reasoning …

Forgotten Topological Index And Its Properties On Neutrosophic Graphs, G. Vetrivel, M. Mullai, R. Buvaneshwari

Neutrosophic Systems with Applications

Topological indices play a significant role in crisp, fuzzy graphs and their real-life application. But to avoid the vagueness in the final result, these indices should be dealt with in the neutrosophic environment since it consolidates the uncertain quantity or values of an event in the name of "indeterminacy membership". Except for the wiener index, no other indices are introduced under the neutrosophic graphical setting. In this article, we consider the forgotten topological index (ToI) and the Edge forgotten index in the 3-valued logic neutrosophic graph and came up with some important theorem results and applications.

Some Operations On Neutrosophic Hypersoft Matrices And Their Applications, Jayasudha J, Raghavi S

Neutrosophic Systems with Applications

This paper aims to extend the concept of Neutrosophic Hypersoft Matrix (NHSM) theory. NHSM is the matrix representation of a Neutrosophic Hypersoft Set (NHSS), where NHSS is the combination of a Neutrosophic set and a Hypersoft set. An NHSS can be stored in computer memory using the matrix notion, which is very useful and applicable. Based on NHSM, we provide some new notions (operations) such as NHS-sub-matrix, Equal NHSM, Null NHSM, Universal NHSM, Complement NHSM, NH-choice matrix (NHCM), product of NHCM and combined NHCM along with examples and characterizations. Additionally, we develop an NHSM algorithm using a value matrix, grace …

Image-Guided Patient-Specific Optimization Of Catheter Placement For Convection-Enhanced Nanoparticle Delivery In Recurrent Glioblastoma, Chengyue Wu, David A Hormuth, Chase D Christenson, Ryan T Woodall, Michael R A Abdelmalik, William T Phillips, Thomas J R Hughes, Andrew J Brenner, Thomas E Yankeelov

Faculty, Staff and Student Publications

Background: Proper catheter placement for convection-enhanced delivery (CED) is required to maximize tumor coverage and minimize exposure to healthy tissue. We developed an image-based model to patient-specifically optimize the catheter placement for rhenium-186 (186Re)-nanoliposomes (RNL) delivery to treat recurrent glioblastoma (rGBM).

Methods: The model consists of the 1) fluid fields generated via catheter infusion, 2) dynamic transport of RNL, and 3) transforming RNL concentration to the SPECT signal. Patient-specific tissue geometries were assigned from pre-delivery MRIs. Model parameters were personalized with either 1) individual-based calibration with longitudinal SPECT images, or 2) population-based assignment via leave-one-out cross-validation. The concordance correlation coefficient …

Performance Of 5 Prominent Large Language Models In Surgical Knowledge Evaluation: A Comparative Analysis, Adam M. Ostrovsky, Joshua R. Chen, Vishal N. Shah, Babak Abai

Department of Surgery Faculty Papers

No abstract provided.

The Impact Of Managerial Myopia On Cybersecurity: Evidence From Data Breaches, Wen Chen, Xing Li, Haibin Wu, Liandong Zhang

Research Collection School Of Accountancy

Using a sample of U.S. firms for the period 2005–2017, we provide evidence that managerial myopic actions contribute to corporate cybersecurity risk. Specifically, we show that abnormal cuts in discretionary expenditures, our proxy for managerial myopia, are positively associated with the likelihood of data breaches. The association is largely driven by firms that appear to cut discretionary expenditures to meet short-term earnings targets. In addition, the association is stronger for firms with greater short-term equity incentives, higher earnings response coefficients, low levels of institutional block ownership, or large market shares. Finally, firms appear to increase discretionary expenditures upon the announcement …

Adavis: Adaptive And Explainable Visualization Recommendation For Tabular Data, Songheng Zhang, Haotian Li, Huamin Qu, Yong Wang

Research Collection School Of Computing and Information Systems

Automated visualization recommendation facilitates the rapid creation of effective visualizations, which is especially beneficial for users with limited time and limited knowledge of data visualization. There is an increasing trend in leveraging machine learning (ML) techniques to achieve an end-to-end visualization recommendation. However, existing ML-based approaches implicitly assume that there is only one appropriate visualization for a specific dataset, which is often not true for real applications. Also, they often work like a black box, and are difficult for users to understand the reasons for recommending specific visualizations. To fill the research gap, we propose AdaVis, an adaptive and explainable …

Face It Yourselves: An Llm-Based Two-Stage Strategy To Localize Configuration Errors Via Logs, Shiwen Shi, Yintong Huo, Yuxin Su, Yichen Li, Dan Li, Zibin Zheng

Research Collection School Of Computing and Information Systems

Configurable software systems are prone to configuration errors, resulting in significant losses to companies. However, diagnosing these errors is challenging due to the vast and complex configuration space. These errors pose significant challenges for both experienced maintainers and new end-users, particularly those without access to the source code of the software systems. Given that logs are easily accessible to most end-users, we conduct a preliminary study to outline the challenges and opportunities of utilizing logs in localizing configuration errors. Based on the insights gained from the preliminary study, we propose an LLM-based two-stage strategy for end-users to localize the root-cause …

How Effective Are They? Exploring Large Language Model Based Fuzz Driver Generation, Cen Zhang, Yaowen Zheng, Mingqiang Bai, Yeting Li, Wei Ma, Xiaofei Xie

Research Collection School Of Computing and Information Systems

Fuzz drivers are essential for library API fuzzing. However, automatically generating fuzz drivers is a complex task, as it demands the creation of high-quality, correct, and robust API usage code. An LLM-based (Large Language Model) approach for generating fuzz drivers is a promising area of research. Unlike traditional program analysis-based generators, this text-based approach is more generalized and capable of harnessing a variety of API usage information, resulting in code that is friendly for human readers. However, there is still a lack of understanding regarding the fundamental issues on this direction, such as its e ectiveness and potential challenges. To …

Fintech Digital Transformation: Generative Ai, Humanoid Robots, Metaverse, Human-Ai Collaboration, And Industry 5.0, Yuxin Liu, Runyu Wang, Keng Siau

Research Collection School Of Computing and Information Systems

This paper discusses the transformative impact of emerging digital technologies on the digital transformation of the financial industry, focusing on integrating Generative AI (GenAI), humanoid robots, and the Metaverse within the framework of Industry 5.0. Industry 5.0 emphasizes a human-centric approach to technology, where human-AI collaboration plays a central role in reshaping financial services. By reviewing both academic research and practical applications, the paper highlights the current advancements in FinTech, particularly in AI technologies and the Metaverse, and their future potential, demonstrating how these innovations are driving growth, efficiency, and resilience in the financial sector. Further, the paper proposes a …

Multi-Scale Variational Autoencoder For Imputation Of Missing Values In Untargeted Metabolomics Using Whole-Genome Sequencing Data, Chen Zhao, Kuan-Jui Su, Chong Wu, Xuewei Cao, Qiuying Sha, Wu Li, Zhe Luo, Tian Qing, Chuan Qiu, Lan Juan Zhao, Anqi Liu, Lindong Jiang, Xiao Zhang, Hui Shen, Weihua Zhou, Hong-Wen Deng

Faculty, Staff and Student Publications

Background: Missing data is a common challenge in mass spectrometry-based metabolomics, which can lead to biased and incomplete analyses. The integration of whole-genome sequencing (WGS) data with metabolomics data has emerged as a promising approach to enhance the accuracy of data imputation in metabolomics studies.

Method: In this study, we propose a novel method that leverages the information from WGS data and reference metabolites to impute unknown metabolites. Our approach utilizes a multi-scale variational autoencoder to jointly model the burden score, polygenetic risk score (PGS), and linkage disequilibrium (LD) pruned single nucleotide polymorphisms (SNPs) for feature extraction and missing metabolomics …

Getting To The Point: Contrasting Directness And Warmth In Motivational Embodied Conversational Agents, Michael O'Mahony, Cathy Ennis, Robert Ross

Conference papers

Enhancing long-term engagement with conversational agents remains a significant challenge. Controlling the perceived warmth or directness of an agent’s personality through the style of its generated text could be used to increase user likeability. This paper reports an investigation of a Wizard-of-Oz (WoZ) mediated study of two variants of a motivational embodied conversational agent to measure user perception of and attitudes towards warmth in interaction style. Results show a significant effect of users preferring an agent with a "more direct" personality for this scenario, though this effect is in many ways nuanced.

Efficient And Secure Federated Learning Against Backdoor Attacks, Yinbin Miao, Rongpeng Xie, Xinghua Li, Zhiquan Liu, Kim-Kwang Raymond Choo, Robert H. Deng

Research Collection School Of Computing and Information Systems

Due to the powerful representation ability and superior performance of Deep Neural Networks (DNN), Federated Learning (FL) based on DNN has attracted much attention from both academic and industrial fields. However, its transmitted plaintext data causes privacy disclosure. FL based on Local Differential Privacy (LDP) solutions can provide privacy protection to a certain extent, but these solutions still cannot achieve adaptive perturbation in DNN model. In addition, this kind of schemes cause high communication overheads due to the curse of dimensionality of DNN, and are naturally vulnerable to backdoor attacks due to the inherent distributed characteristic. To solve these issues, …