Digital Commons Network^™

Stealthy Backdoor Attack For Code Models, Zhou Yang, Bowen Xu, Jie M. Zhang, Hong Jin Kang, Jieke Shi, Junda He, David Lo

Research Collection School Of Computing and Information Systems

Code models, such as CodeBERT and CodeT5, offer general-purpose representations of code and play a vital role in supporting downstream automated software engineering tasks. Most recently, code models were revealed to be vulnerable to backdoor attacks. A code model that is backdoor-attacked can behave normally on clean examples but will produce pre-defined malicious outputs on examples injected with that activate the backdoors. Existing backdoor attacks on code models use unstealthy and easy-to-detect triggers. This paper aims to investigate the vulnerability of code models with backdoor attacks. To this end, we propose A (dversarial eature as daptive Back). A achieves stealthiness …

Editorial: Emerging On-Demand Passenger And Logistics Systems: Modelling, Optimization, And Data Analytics, Jintao Ke, Hai Wang, Neda Masoud, Maximilian Schiffer, Goncalo H. A. Correia

Research Collection School Of Computing and Information Systems

The proliferation of smart personal devices and mobile internet access has fueled numerous advancements in on-demand transportation services. These services are facilitated by online digital platforms and range from providing rides to delivering products. Their influence is transforming transportation systems and leaving a mark on changing individual mobility, activity patterns, and consumption behaviors. For instance, on-demand transportation companies such as Uber, Lyft, Grab, and DiDi have become increasingly vital for meeting urban transportation needs by connecting available drivers with passengers in real time. The recent surge in door-to-door food delivery (e.g., Uber Eats, DoorDash, Meituan); grocery delivery (e.g., Amazon Fresh, …

Marco: A Stochastic Asynchronous Concolic Explorer, Jie Hu, Yue Duan, Heng Yin

Research Collection School Of Computing and Information Systems

Concolic execution is a powerful program analysis technique for code path exploration. Despite recent advances that greatly improved the efficiency of concolic execution engines, path constraint solving remains a major bottleneck of concolic testing. An intelligent scheduler for inputs/branches becomes even more crucial. Our studies show that the previously under-studied branch-flipping policy adopted by state-of-the-art concolic execution engines has several limitations. We propose to assess each branch by its potential for new code coverage from a global view, concerning the path divergence probability at each branch. To validate this idea, we implemented a prototype Marco and evaluated it against the …

Acav: A Framework For Automatic Causality Analysis In Autonomous Vehicle Accident Recordings, Huijia Sun, Christopher M. Poskitt, Yang Sun, Jun Sun, Yuqi Chen

Research Collection School Of Computing and Information Systems

The rapid progress of autonomous vehicles (AVs) has brought the prospect of a driverless future closer than ever. Recent fatalities, however, have emphasized the importance of safety validation through large-scale testing. Multiple approaches achieve this fully automatically using high-fidelity simulators, i.e., by generating diverse driving scenarios and evaluating autonomous driving systems (ADSs) against different test oracles. While effective at finding violations, these approaches do not identify the decisions and actions that caused them -- information that is critical for improving the safety of ADSs. To address this challenge, we propose ACAV, an automated framework designed to conduct causality analysis for …

Teaching Software Development For Real-World Problems Using A Microservice-Based Collaborative Problem-Solving Approach, Yi Meng Lau, Christian Michael Koh, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Experienced and skillful software developers are needed in organizations to develop software products effective for their business with shortened time-to-market. Such developers will not only need to code but also be able to work in teams and collaboratively solve real-world problems that organizations arefacing. It is challenging for educators to nurture students to become such developers with strong technical, social, and cognitive skills. Towards addressing the challenge, this study presents a Collaborative Software Development Project Framework for a course that focuses on learning microservices architectures anddeveloping a software application for a real-world business. Students get to work in teams to …

Performing Information Extraction For Mission Engineering Applications, Samuel R. Koski

Engineering Management & Systems Engineering Theses & Dissertations

The process of extracting structured data from unstructured and semi-structured text is manual, time consuming and error prone. Current natural language processing approaches for automating this process are difficult to verify for non-trivial and context-sensitive corpora. Large Language Models (LLMs) like ChatGPT have become a subject of considerable interest, opening a promising avenue of exploration. However, there is limited evidence on the performance of LLMs for information extraction.

In this dissertation, an approach is proposed to evaluate the accuracy of Stanford OpenIE and OpenAI's ChatGPT for this purpose. This includes comparing Resource Description Framework (RDF) triples extracted by each of …

Enabling Sustainable Mining Via Ai-Based Techniques, Nurul Asyikeen Binte Azhar

Dissertations and Theses Collection (Open Access)

The precedence-constrained production scheduling problem (PCPSP) in Long-Term Mine Planning (LTMP) is NP-hard and conventionally prioritizes the Net Present Value (NPV) of profits. Even so, heightened sustainability concerns necessitate heightened sustainable practices. Yet, research still lags. This dissertation addresses this paucity by integrating sustainability elements through Multi-Objective Optimization (MOO), introducing novel algorithms and proposing an uncertainty assessment within a dual Multi-Objective Evolutionary Algorithm (MOEA) setup.

Firstly, our systematic review of past LTMP research focused on the PCPSP and highlighted sustainability elements. Overall, it furnished real-world components incorporated into mathematical formulations, trends, quality of solutions (efficacy) and computation time (efficiency) of …

Intelligent Tutoring System Ontology, Wael Mohamed Hassan

Theses

The integration of pedagogical rules into Intelligent Tutoring Systems (ITS) using semantic web technologies, particularly the Web Ontology Language (OWL), holds great promise for enhancing the capabilities of these systems. However, a significant challenge arises from the labor-intensive process of manually constructing ontologies, which can consume valuable time and resources. While ontologies offer numerous advantages, including robust knowledge inference and scalability, the limitations of manual ontology creation are evident in terms of time and flexibility. Therefore, the primary objective of this research is to develop an efficient and automated solution that harnesses the benefits of ontologies while reducing the time …

Implementation And Evaluation Of Ai-Based Citizen Question-Answer Recommender (Acqar) To Enhance Citizen Service Delivery In Singapore Public Sector: A Case Study, Hui Shan Lee

Dissertations and Theses Collection (Open Access)

Government agencies prioritize citizen service delivery to foster trust with the public. Technological advancements, particularly in Artificial Intelligence (AI), hold promise for improving service provision and aligning government operations with citizens' needs. Yet the inherent inflexibility of Service Level Agreements (SLAs) often overlooks the nuances of human emotions and the varied nature of citizen inquiries, exacerbated by a lack of tools to guide appropriate responses. This dissertation aims to address the gaps of overlook of human emotions and non-support for appropriate responses, by exploring the following questions: (1) Can a predictive model incorporating both numeric and textual data effectively forecast …

Can Organizational Focus On Responsible Ai Lead To Improved Ai Adoption By Employees?, Seema Chokshi

Dissertations and Theses Collection (Open Access)

The duality inherent in Artificial Intelligence technology entails that while AI has the potential to bring about transformative benefits to organizations, unintended consequences of AI applications could lead to biased and discriminatory outcomes, which could have negative consequences for the organization and society in general. Concerns about such unintended consequences are an impediment to AI adoption where unwilling employees and practitioners often fear ethical breaches, thereby, negatively impacting their engagement with AI driven applications. In response to these concerns various organizations and regulatory bodies have developed governing frameworks broadly known as Responsible AI standards, that set guidelines to design, …

Sequential Recommendation: From Representation Learning To Reasoning, Lei Wang

Dissertations and Theses Collection (Open Access)

The recommender system is a crucial component of today's online services. It helps users navigate through an overwhelmingly large number of items and discovering those that interest them. Unlike general recommender systems, which recommend items based on the user's overall preferences, sequential recommender systems consider the order of user-item interactions. Sequential recommendations aim to predict the next item a user will interact with, given a sequence of previously interacted items, while considering the short-term and long-term dependencies among items.

In this thesis, we focus on sequential recommendation methods: from representation learning to large language model (LLM)-based reasoning. On the one …

Mut: Human-In-The-Loop Unit Test Migration, Yi Gao, Xing Hu, Tongtong Xu, Xin Xia, David Lo, Xiaohu Yang

Research Collection School Of Computing and Information Systems

Test migration, which enables the reuse of test cases crafted with knowledge and creativity by testers across various platforms and programming languages, has exhibited effectiveness in mobile app testing. However, unit test migration at the source code level has not garnered adequate attention and exploration. In this paper, we propose a novel cross-language and cross-platform test migration methodology, named MUT, which consists of four modules: code mapping, test case filtering, test case translation, and test case adaptation. MUT initially calculates code mappings to establish associations between source and target projects, and identifies suitable unit tests for migration from the source …

Deep Reinforcement Learning For Dynamic Algorithm Selection: A Proof-Of-Principle Study On Differential Evolution, Hongshu Guo, Yining Ma, Zeyuan Ma, Jiacheng Chen, Xinglin Zhang, Zhiguang Cao, Jun Zhang, Yue-Jiao Gong

Research Collection School Of Computing and Information Systems

Evolutionary algorithms, such as differential evolution, excel in solving real-parameter optimization challenges. However, the effectiveness of a single algorithm varies across different problem instances, necessitating considerable efforts in algorithm selection or configuration. This article aims to address the limitation by leveraging the complementary strengths of a group of algorithms and dynamically scheduling them throughout the optimization progress for specific problems. We propose a deep reinforcement learning-based dynamic algorithm selection framework to accomplish this task. Our approach models the dynamic algorithm selection a Markov decision process, training an agent in a policy gradient manner to select the most suitable algorithm according …

Discovering Significant Topics From Legal Decisions With Selective Inference, Jerrold Tsin Howe Soh

Research Collection Yong Pung How School Of Law

We propose and evaluate an automated pipeline for discovering significant topics from legal decision texts by passing features synthesized with topic models through penalized regressions and post-selection significance tests. The method identifies case topics significantly correlated with outcomes, topic-word distributions which can be manually interpreted to gain insights about significant topics, and case-topic weights which can be used to identify representative cases for each topic. We demonstrate the method on a new dataset of domain name disputes and a canonical dataset of European Court of Human Rights violation cases. Topic models based on latent semantic analysis as well as language …

Ct Image Segmentation Using Optimization Techniques Under Neutrosophic Domain, Doaa El-Shahat, Nourhan Talal, Jun Ye, Wen-Hua Cui

Neutrosophic Systems with Applications

In this paper, we introduce a hybrid technique between optimization algorithms and neutrosophic theory. This new hybridization can deal with uncertainties in brain computed tomography (CT) images in three different memberships very effectively. To prove the real-time application of this theory, a new segmentation method for brain CT medical images is presented. The grayscale medical image suffers from uncertainties and inconsistencies in the gray levels due to their bad luminance. The proposed technique addressed this problem by performing neutrosophic operations on gray levels based on the S membership function.

Testing The Capability Of Ai Art Tools For Urban Design, Connor Phillips, Junfeng Jiao, Emmalee Clubb

Research Collection College of Integrative Studies

This study aimed to evaluate the performance of three artificial intelligence (AI) image synthesis models, Dall-E 2, Stable Diffusion, and Midjourney, in generating urban design imagery based on scene descriptions. A total of 240 images were generated and evaluated by two independent professional evaluators using an adapted sensibleness and specificity average metric. The results showed significant differences between the three AI models, as well as differing scores across urban scenes, suggesting that some projects and design elements may be more challenging for AI art generators to represent visually. Analysis of individual design elements showed high accuracy in common features like …

Filter-Based Stance Network For Rumor Verification, Jun Li, Yi Bin, Yunshan Ma, Yang Yang, Zi Huang, Tat‑Seng Chua

Research Collection School Of Computing and Information Systems

Rumor verification on social media aims to identify the truth value of a rumor, which is important to decreasethe detrimental public effects. A rumor might arouse heated discussions and replies, conveying differentstances of users that could be helpful in identifying the rumor. Thus, several works have been proposedto verify a rumor by modelling its entire stance sequence in the time domain. However, these works ignorethat such a stance sequence could be decomposed into controversies with different intensities, which could beused to cluster the stance sequences with the same consensus. In addition, the existing stance extractors fail toconsider both the impact …

Hop‑Based Heterogeneous Graph Transformer, Zixuan Yang, Xiao Wang, Yanhua Yu, Yuling Wang, Kangkang Lu, Zirui Guo, Xiting Qin, Yunshan Ma, Tat‑Seng Chua

Research Collection School Of Computing and Information Systems

The Graph Transformer (GT) has shown significant ability in processing graph-structured data, addressing limitations in graph neural networks, such as over-smoothing and over-squashing. However, the implementation of GT in real-world heterogeneous graphs (HGs) with complex topology continues to present numerous challenges. Firstly, a challenge arises in designing a tokenizer that is compatible with heterogeneity. Secondly, the complexity of the transformer hampers the acquisition of high-order neighbor information in HGs. In this paper, we propose a novel Hop-basedHeterogeneous Graph Transformer (H2Gormer) framework, paving a promising path for HGs to benefit from the capabilities of Transformers. We propose a Heterogeneous Hop-based Token …

Exploring The Potential Of Chatgpt In Automated Code Refinement: An Empirical Study, Qi Guo, Shangqing Liu, Junming Cao, Xiaohong Li, Xin Peng, Xiaofei Xie, Bihuan Chen

Research Collection School Of Computing and Information Systems

Code review is an essential activity for ensuring the quality and maintainability of software projects. However, it is a time-consuming and often error-prone task that can significantly impact the development process. Recently, ChatGPT, a cutting-edge language model, has demonstrated impressive performance in various natural language processing tasks, suggesting its potential to automate code review processes. However, it is still unclear how well ChatGPT performs in code review tasks. To fill this gap, in this paper, we conduct the first empirical study to understand the capabilities of ChatGPT in code review tasks, specifically focusing on automated code refinement based on given …

W4-Groups: Modeling The Who, What, When And Where Of Group Behavior Via Mobility Sensing, Akansha Atrey, Camellia Zakaria, Rajesh Krishna Balan, Prashant Shenoy

Research Collection School Of Computing and Information Systems

Human social interactions occur in group settings of varying sizes and locations, depending on the type of social activity. The ability to distinguish group formations based on their purposes transforms how group detection mechanisms function. Not only should such tools support the effective detection of serendipitous encounters, but they can derive categories of relation types among users. Determining who is involved, what activity is performed, and when and where the activity occurs are critical to understanding group processes in greater depth, including supporting goal-oriented applications (e.g., performance, productivity, and mental health) that require sensing social factors. In this work, we …

Experience Report: Identifying Common Misconceptions And Errors Of Novice Programmers With Chatgpt, Hua Leong Fwa

Research Collection School Of Computing and Information Systems

Identifying the misconceptions of novice programmers is pertinent for informing instructors of the challenges faced by their students in learning computer programming. In the current literature, custom tools, test scripts were developed and, in most cases, manual effort to go through the individual codes were required to identify and categorize the errors latent within the students' code submissions. This entails investment of substantial effort and time from the instructors. In this study, we thus propose the use of ChatGPT in identifying and categorizing the errors. Using prompts that were seeded only with the student's code and the model code solution …

Improving Automated Code Reviews: Learning From Experience, Hong Yi Lin, Patanamon Thongtanunam, Christoph Treude, Wachiraphan Charoenwet

Research Collection School Of Computing and Information Systems

Modern code review is a critical quality assurance process that is widely adopted in both industry and open source software environments. This process can help newcomers learn from the feedback of experienced reviewers; however, it often brings a large workload and stress to reviewers. To alleviate this burden, the field of automated code reviews aims to automate the process, teaching large language models to provide reviews on submitted code, just as a human would. A recent approach pre-trained and fine-tuned the code intelligent language model on a large-scale code review corpus. However, such techniques did not fully utilise quality reviews …

Beyond A Joke: Dead Code Elimination Can Delete Live Code, Haoxin Tu, Lingxiao Jiang, Debin Gao, He Jiang

Research Collection School Of Computing and Information Systems

Dead Code Elimination (DCE) is a fundamental compiler optimization technique that removes dead code (e.g., unreachable or reachable but whose results are unused) in the program to produce smaller or faster executables. However, since compiler optimizations are typically aggressively performed and there are complex relationships/interplay among a vast number of compiler optimizations (including DCE), it is not known whether DCE is indeed correctly performed and will only delete dead code in practice. In this study, we open a new research problem to investigate: can DCE happen to erroneously delete live code? To tackle this problem, we design a new approach …

Creative And Correct: Requesting Diverse Code Solutions From Ai, Scott Blyth, Markus Wagner, Christoph Treude

Research Collection School Of Computing and Information Systems

AI foundation models have the capability to produce a wide array of responses to a single prompt, a feature that is highly beneficial in software engineering to generate diverse code solutions. However, this advantage introduces a significant trade-off between diversity and correctness. In software engineering tasks, diversity is key to exploring design spaces and fostering creativity, but the practical value of these solutions is heavily dependent on their correctness. Our study systematically investigates this trade-off using experiments with HumanEval tasks, exploring various parameter settings and prompting strategies. We assess the diversity of code solutions using similarity metrics from the code …

Enhancing Source Code Representations For Deep Learning With Static Analysis, Xueting Guan, Christoph Treude

Research Collection School Of Computing and Information Systems

Deep learning techniques applied to program analysis tasks such as code classification, summarization, and bug detection have seen widespread interest. Traditional approaches, however, treat programming source code as natural language text, which may neglect significant structural or semantic details. Additionally, most current methods of representing source code focus solely on the code, without considering beneficial additional context. This paper explores the integration of static analysis and additional context such as bug reports and design patterns into source code representations for deep learning models. We use the Abstract Syntax Tree-based Neural Network (ASTNN) method and augment it with additional context information …

Impact Of Government Outsourcing Contracts On High-Tech Vendors: An Empirical Study, Yi Dong, Nan Hu, Yonghua Ji, Chenkai Ni, Jing Xie

Research Collection School Of Computing and Information Systems

Outsourcing is an important strategic decision of high-tech firms. However, while the research has extensively studied the implications of outsourcing to high-tech clients, its impact on high-tech vendors remains underexplored. This study empirically estimates the impact of government outsourcing contracts on high-tech vendors. Employing the earnings-return analyses framework, we find that, for high-tech vendors engaged in government outsourcing contracts, the stock market places a higher value on each unit of unexpected earnings compared to other firms. Additionally, this impact becomes stronger for contracts with longer terms, for contracts outsourced by the U.S. government or by countries with better political and …

Unveiling Memorization In Code Models, Zhou Yang, Zhipeng Zhao, Chenyu Wang, Jieke Shi, Dongsun Kim, Donggyun Han, David Lo

Research Collection School Of Computing and Information Systems

The availability of large-scale datasets, advanced architectures, and powerful computational resources have led to effective code models that automate diverse software engineering activities. The datasets usually consist of billions of lines of code from both open-source and private repositories. A code model memorizes and produces source code verbatim, which potentially contains vulnerabilities, sensitive information, or code with strict licenses, leading to potential security and privacy issues.This paper investigates an important problem: to what extent do code models memorize their training data? We conduct an empirical study to explore memorization in large pre-trained code models. Our study highlights that simply extracting …

Out Of Sight, Out Of Mind: Better Automatic Vulnerability Repair By Broadening Input Ranges And Sources, Xin Zhou, Kisub Kim, Bowen Xu, Donggyun Han, David Lo

Research Collection School Of Computing and Information Systems

The advances of deep learning (DL) have paved the way for automatic software vulnerability repair approaches, which effectively learn the mapping from the vulnerable code to the fixed code. Nevertheless, existing DL-based vulnerability repair methods face notable limitations: 1) they struggle to handle lengthy vulnerable code, 2) they treat code as natural language texts, neglecting its inherent structure, and 3) they do not tap into the valuable expert knowledge present in the expert system. To address this, we propose VulMaster, a Transformer-based neural network model that excels at generating vulnerability repairs by comprehensively understanding the entire vulnerable code, irrespective of …

Ps3: Precise Patch Presence Test Based On Semantic Symbolic Signature, Qi Zhan, Xing Hu, Zhiyang Li, Xin Xia, David Lo, Shanping Li

Research Collection School Of Computing and Information Systems

During software development, vulnerabilities have posed a significant threat to users. Patches are the most effective way to combat vulnerabilities. In a large-scale software system, testing the presence of a security patch in every affected binary is crucial to ensure system security. Identifying whether a binary has been patched for a known vulnerability is challenging, as there may only be small differences between patched and vulnerable versions. Existing approaches mainly focus on detecting patches that are compiled in the same compiler options. However, it is common for developers to compile programs with very different compiler options in different situations, which …

Coca: Improving And Explaining Graph Neural Network-Based Vulnerability Detection Systems, Sicong Cao, Xiaobing Sun, Xiaoxue Wu, David Lo, Lili Bo, Bin Li, Wei Liu

Research Collection School Of Computing and Information Systems

Recently, Graph Neural Network (GNN)-based vulnerability detection systems have achieved remarkable success. However, the lack of explainability poses a critical challenge to deploy black-box models in security-related domains. For this reason, several approaches have been proposed to explain the decision logic of the detection model by providing a set of crucial statements positively contributing to its predictions. Unfortunately, due to the weakly-robust detection models and suboptimal explanation strategy, they have the danger of revealing spurious correlations and redundancy issue.In this paper, we propose Coca, a general framework aiming to 1) enhance the robustness of existing GNN-based vulnerability detection models to …