Digital Commons Network^™

Filterfl: Knowledge Filtering-Based Data-Free Backdoor Defense For Federated Learning, Yanxin Yang, Ming Hu, Xiaofei Xie, Yue Cao, Pengyu Zhang, Yihao Huang, Mingsong Chen

Research Collection School Of Computing and Information Systems

As a distributed machine learning paradigm, Federated Learning (FL) enables large-scale clients to collaboratively train a model without sharing their raw data. However, due to the lack of data auditing for untrusted clients, FL is vulnerable to poisoning attacks, especially backdoor attacks. By using poisoned data for local training or directly changing the model parameters, attackers can easily inject backdoors into the model, which can trigger the model to make misclassification of targeted patterns in images. To address these issues, we propose a novel data-free trigger-generation-based defense approach based on the two characteristics of backdoor attacks: i) triggers are learned …

Cross-Subject Mind Decoding From Inaccurate Representations, Yangyang Xu, Bangzhen Liu, Wenqi Shao, Yong Du, Shengfeng He, Tingting Zhu

Research Collection School Of Computing and Information Systems

Decoding stimulus images from fMRI signals has advanced with pre-trained generative models. However, existing methods struggle with cross-subject mappings due to cognitive variability and subject-specific differences. This challenge arises from sequential errors, where unidirectional mappings generate partially inaccurate representations that, when fed into diffusion models, accumulate errors and degrade reconstruction fidelity. To address this, we propose the Bidirectional Autoencoder Intertwining framework for accurate decoded representation prediction. Our approach unifies multiple subjects through a Subject Bias Modulation Module while leveraging bidirectional mapping to better capture data distributions for precise representation prediction. To further enhance fidelity when decoding representations into stimulus images, …

Boosting Chart-To-Code Generation In Mllm Via Dual Preference-Guided Refinement, Zhihan Zhang, Yixin Cao, Lizi Liao

Research Collection School Of Computing and Information Systems

Translating chart images into executable plotting scripts-referred to as the chart-to-code generation task-requires Multimodal Large Language Models (MLLMs) to perform fine-grained visual parsing, precise code synthesis, and robust cross-modal reasoning. However, this task is inherently under-constrained: multiple valid code implementations can produce the same visual chart, and evaluation must consider both code correctness and visual fidelity across diverse dimensions. This makes it difficult to learn accurate and generalizable mappings through standard supervised fine-tuning. To address these challenges, we propose a dual preference-guided refinement framework that combines a feedback-driven, dual-modality reward mechanism with iterative preference learning. Our approach introduces a structured …

Ivycross: A Privacy-Preserving And Concurrency Control Framework For Blockchain Interoperability, Ming Li, Jian Weng, Jia-Si Weng, Yi Li, Yongdong Wu, Dingcheng Li, Guowen Xu, Deng, Robert H.

Research Collection School Of Computing and Information Systems

Interoperability is a fundamental challenge for long-envisioned blockchain applications. A mainstream approach is using Trusted Execution Environment (TEE) to support interoperable off-chain execution. However, this incurs multiple TEE configured with non-trivial storage capabilities running on fragile concurrent processing environments, rendering current strategies based on TEE far from being practical. This paper aims to fill this gap and design a practical interoperability mechanism with simplified TEE as the underlying architecture. Specifically, we present IvyCross, a TEE-based framework that achieves low-cost, privacy-preserving, and race-free blockchain interoperability. IvyCross allows running arbitrary smart contracts across heterogeneous blockchains atop two distributed TEE-powered hosts. We design …

Auxiliary Prompt Tuning Of Vision‑Language Models For Few‑Shot Out‑Of‑Distribution Detection, Wenjun Miao, Guansong Pang, Zihan Wang, Jin Zheng, Xiao Bai

Research Collection School Of Computing and Information Systems

Recent advancements in CLIP-based out-of-distribution (OOD) detection have shown promising results via regularization on prompt tuning, leveraging background features extracted from a few in-distribution (ID) samples as proxies for OOD features.However, these methods suffer from an inherent limitation: a lack of diversity in the extracted OOD features from the few-shot ID data.To address this issue, we propose to leverage external datasets as auxiliary outlier data (i.e., pseudo OOD samples) to extract rich, diverse OOD features, with the features from not only background regions but also foreground object regions, thereby supporting more discriminative prompt tuning for OOD detection. We further introduce …

Contrastrepair: Enhancing Conversation-Based Automated Program Repair Via Contrastive Test Case Pairs, Jiaolong Kong, Xiaofei Xie, Mingfei Cheng, Shangqing Liu, Xiaoning Du, Qi Guo

Research Collection School Of Computing and Information Systems

Automated Program Repair (APR) aims to automatically generate patches for rectifying software bugs. Recentstrides in Large Language Models (LLM), such as ChatGPT, have yielded encouraging outcomes in APR,especially within the conversation-driven APR framework. Nevertheless, the efficacy of conversation-drivenAPR is contingent on the quality of the feedback information. In this article, we propose ContrastRepair, anovel conversation-based APR approach that augments conversation-driven APR by providing LLMs withcontrastive test pairs. A test pair consists of a failing test and a passing test, which offer contrastive feedback tothe LLM. Our key insight is to minimize the difference between the generated passing test and the …

Polyqent: A Polynomial Quantified Entailment Solver, Krishnendu Chatterjee, Amir Kafshdar Goharshady, Ehsan Kafshdar Goharshady, Mehrdad Karrabi, Milad Saadat, Maximilian Seeliger, Dorde Zikelic

Research Collection School Of Computing and Information Systems

Polynomial quantified entailments with existentially and universally quantified variables arise in many problems of verification and program analysis. We present PolyQEnt which is a tool for solving polynomial quantified entailments in which variables on both sides of the implication are real valued or unbounded integers. Our tool provides a unified framework for polynomial quantified entailment problems that arise in several papers in the literature. Our experimental evaluation over a wide range of benchmarks shows the applicability of the tool as well as its benefits as opposed to simply using existing SMT solvers to solve such constraints.

Interpreting The Private‑ And Public‑Sector Service Criteria For Singapore’S Aspiring Presidential Candidates, Benjamin Joshua Ong

Research Collection Yong Pung How School Of Law

The Singapore President's role is not only ceremonial: from 1991, it has encompassed the substantive function of serving as a guardian of public reserves and the integrity of the public service. A person must meet certain qualifying criteria in order to run in a Presidential election. This article focuses on one set of qualifying criteria, namely, the "service criteria": the requirement that candidates have had certain experience in serving in certain roles in the public sector or the private sector. The service criteria were last amended in 2016, and came to the fore in the 2023 Presidential Election following George …

Beneficial Ownership In Domestic Tax Legislation, Some Clarity, But Far From ‘Well Established’: Hargreaves Property Holdings Ltd V Hmrc [2024] Ewca Civ 365, Vincent Ooi

Research Collection Yong Pung How School Of Law

The concept of beneficial ownership is extensively used in domestic tax legislation, but several decades ofinconsistent case law have muddied the waters as to exactly what it means. With the leading casesstopping short of the apex court, it is difficult to reconcile the cases and come up with a clear definition ofbeneficial ownership. The recent Hargreaves decision by Falk LJ (with whom Nugee and Peter JacksonLJJ agreed) represents the most structured judicial attempt to rationalise the concept to date. This notesuggests that, contrary to Falk LJ’s statement that the concept is ‘well established’, the law pre-Hargreaveswas far from clear. This …

Civil Liability For Invasions Of Privacy: Whither Singapore?, Yu Han Lam

Research Collection Yong Pung How School Of Law

Intrusions upon privacy are becoming increasingly common in Singapore. Singapore has yet to establish a tort addressing this issue, although the SAL Law Reform Committee has proposed a tort of misuse of private information. Australia has also recently introduced a statutory tort of serious invasion of privacy. This article will argue for the need for a Singapore tort of intrusion upon seclusion, on top of the already proposed tort of misuse of private information, to cover more appropriately instances of intrusions upon privacy.

Impacts Of U.S. Environmental Regulations On Industry, Xiao Ji, Mengyu Wang, Tianyi Zhang

Sim Kee Boon Institute for Financial Economics

This paper analyzes the impacts of U.S. environmental regulations on industry, focusing on command-and-control environmental regulations (CCER) and market-based environmental regulations (MBER). Drawing on empirical data from the Environmental Protection Agency (EPA) spanning over four decades, we examine key legislation such as the Clean Water Act (CWA), Clean Air Act (CAA), and the Resource Conservation and Recovery Act (RCRA), while also discussing more recent frameworks like the Inflation Reduction Act (IRA). Our findings suggest that although penalties under CCER contribute to immediate compliance, they often fail to elicit long-term changes in corporate behavior. In contrast, MBER, exemplified by the IRA, …

Learning Orientation Field For Osm-Guided Autonomous Navigation, Yuming Huang, Wei Gao, Zhiyuan Zhang, Maani Ghaffari, Dezhen Song, Cheng-Zhong Xu, Hui Kong

Research Collection School Of Computing and Information Systems

OpenStreetMap (OSM) has gained popularity recently in autonomous navigation due to its public accessibility, lower maintenance costs, and broader geographical coverage. However, existing methods often struggle with noisy OSM data and incomplete sensor observations, leading to inaccuracies in trajectory planning. These challenges are particularly evident in complex driving scenarios, such as at intersections or facing occlusions. To address these challenges, we propose a robust and explainable two-stage framework to learn an Orientation Field (OrField) for robot navigation by integrating LiDAR scans and OSM routes. In the first stage, we introduce a novel representation, OrField, which can provide orientations for each …

Merit Transference And The Paradox Of Merit Inflation, Matthew Hammerton

Research Collection School of Social Sciences

Many religious traditions and ethical systems hold that individuals accrue merit through their good intentions, acts, and character, and demerit through their bad intentions, acts, and character. This merit and demerit, accumulated by individuals throughout their lives, gives each person a kind of ethical “score” that can determine what they deserve, and influence whether good or bad things happen to them (e.g., divine punishments and rewards, a favourable or unfavourable rebirth, etc.). In some traditions (most notably Buddhism, but also to a limited extent in Hinduism, Islam, and Christianity), “merit transference” is a feature of these merit-based ethical systems. This …

Firm Digitalization And Accounting Jobs, Amanda Awyong, Qiang Cheng, Tian Deng, Rencheng Wang

Research Collection School Of Accountancy

This study examines how firm digitalization affects the demand for corporate accountants and their digital skills. Using more than 373,000 job posts for corporate accountants by U.S. non-technology firms between 2010 and 2019, we find that firm digitalization does not change the overall demand for financial specialists-accountants who are responsible for financial reporting, budgeting, and forecasting-but reduces the demand for financial clerks-accountants who primarily perform administrative financial tasks. We further show that firms digitalization increases the demand for digital skills among financial specialists, but not among financial clerks, and that such demand is greater than that for other employees within …

Boosting Symbolic Execution For Vulnerability Detection, Haoxin Tu

Dissertations and Theses Collection (Open Access)

Software systems written by humans tend to be unreliable and insecure, hence, bugs or vulnerabilities in them are inevitable. Symbolic execution has shown considerable potential in detecting diverse types of software bugs and also vulnerabilities that have severe security implications. However, existing symbolic execution engines still suffer from at least three fundamental limitations in memory modeling, path exploration, and structured input generation, which significantly impede existing engines from efficiently and effectively detecting software bugs and vulnerabilities.

The objective of this dissertation is to boost existing symbolic execution engines by designing a new memory model, two new path exploration strategies, and …

Memory-Efficient Graph Processing On Gpus: Reducing Intermediate Data Structure Overhead, Chang Ye

Dissertations and Theses Collection (Open Access)

The increasing scale of real-world graphs in domains such as fraud detection, community detection, and biological analysis demands high-throughput, memory-efficient graph processing solutions. GPUs offer massive parallelism for accelerating such workloads, and numerous frameworks have been developed to leverage their computational power. These frameworks primarily focus on optimizing scheduling to better align graph processing with GPU architectures. It performs well for algorithms with low memory demands, such as BFS, SSSP, and PageRank. However, for algorithms that require substantial memory, such as label propagation, and subgraph counting, the limited memory capacity of GPUs often becomes a significant bottleneck.

This dissertation addresses …

Storage Location Optimization In Automated Storage And Retrieval Systems: A Deep Reinforcement Learning Approach, Lingjun Wang, Aldy Gunawan, Pieter Vansteenwegen

Research Collection School Of Computing and Information Systems

This study investigates the optimization of storage location in automated storage and retrieval systems (AS/RS). We introduce an optimization approach based on the Deep Q-Network (DQN) algorithm to enhance warehouse task efficiency and minimize stacker travel during storage and retrieval. To accelerate the algorithm training process, we integrate a prioritized experience replay mechanism. Furthermore, we decouple action selection from value estimation within the DQN framework to address the issue of value overestimation. The proposed model is evaluated against three heuristic methods. The experimental results demonstrate that our approach significantly outperforms these baselines.

An Efficient Security-Enhanced Accountable Access Control For Named Data Networking, Jianfei Sun, Yuxian Li, Xuehuan Yang, Guomin Yang, Robert H. Deng

Research Collection School Of Computing and Information Systems

Named Data Networking (NDN) is embraced as the crucial implementation of Information-Centric Networking (ICN), enhancing content distribution and caching efficiency through edge routers. However, existing NDN architectures face significant security and privacy challenges, including: (a) a lack of secure and efficient access control; (b) inadequate support for flexible and selective content management by content publishers; (c) insufficient implementation of accountability and privilege revocation mechanisms. To handle these challenges, we propose ESAS, the first-ever Efficient Security-enhanced Accountable Access Control Scheme for NDN. Specifically, our ESAS incorporates anonymous authentication using group signatures at network routers to prevent unauthorized access, employs key-aggregation-based access …

Educator Perceptions Of Devops Teaching Recommendations And Their Alignment With Common Challenges, Marcelo Romulo Fernandes, Pablo Paiva, Samuel Lucas De Moura Ferino, Roberta Coelho, Christoph Treude, Eduardo Aranha, Uirá Kulesza

Research Collection School Of Computing and Information Systems

DevOps education presents unique pedagogical challenges due to the diversity of tools, rapid technological change, and the multidisciplinary nature of the field. Although previous work has proposed recommendations to address these challenges, it is unclear how educators perceive these recommendations and whether they align with the challenges encountered in practice. In this paper, we present a quantitative and qualitative methods study involving 11 DevOps educators who interacted with Improve, a tool that presents a curated set of educational challenges and recommendations derived from previous literature. Educators indicated which recommendations they already use, which they intend to use, and which challenges …

Rethinking Cognitive Complexity For Unit Tests: Toward A Readability-Aware Metric Grounded In Developer Perception, Wendkûuni C. Ouédraogo, Yinghua Li, Xueqi Dang, Xin Zhou, Anil Koyuncu, Jacques Klein, David Lo, Tegawendé F. Bissyandé

Research Collection School Of Computing and Information Systems

Automatically generated unit tests-from searchbased tools like EvoSuite or LLMs-vary significantly in structure and readability. Yet most evaluations rely on metrics like Cyclomatic Complexity and Cognitive Complexity, designed for functional code rather than test code. Recent studies have shown that SonarSource's Cognitive Complexity metric assigns nearzero scores to LLM-generated tests, yet its behavior on EvoSuitegenerated tests and its applicability to test-specific code structures remain unexplored. We introduce CCTR, a Test-Aware Cognitive Complexity metric tailored for unit tests. CCTR integrates structural and semantic features like assertion density, annotation roles, and test composition patterns-dimensions ignored by traditional complexity models but critical for …

Improving Co-Decoding Based Security Hardening Of Code Llms Leveraging Knowledge Distillation, Dong Li, Shanfu Shu, Meng Yan, Zhongxin Liu, Chao Liu, Xiaohong Zhang, David Lo

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have been widely adopted by developers in software development. However, the massive pretraining code data is not rigorously filtered, allowing LLMs to learn unsafe coding patterns. Several prior studies have demonstrated that code LLMs tend to generate code with potential vulnerabilities. The widespread adoption of intelligent programming assistants poses a significant threat to the software development process. Existing approaches to mitigating this risk primarily involve constructing secure data that are free of vulnerabilities and then retraining or fine-tuning the models. However, such an effort is resource intensive and requires significant manual supervision. When the model parameters …

Exploring Parameter-Efficient Fine-Tuning Techniques For Code Generation With Large Language Models, Martin Weyssow, Xin Zhou, Kisub Kim, David Lo, Houari A. Sahraoui

Research Collection School Of Computing and Information Systems

Large language models (LLMs) demonstrate impressive capabilities to generate accurate code snippets given natural language intents in a zero-shot manner, i.e., without the need for specific fine-tuning. While prior studies have highlighted the advantages of fine-tuning LLMs, this process incurs high computational costs, making it impractical in resource-scarce environments, particularly for models with billions of parameters. To address these challenges, previous research explored in-context learning (ICL) and retrieval-augmented generation (RAG) as strategies to guide the LLM generative process with task-specific prompt examples. However, ICL and RAG introduce inconveniences, such as the need for designing contextually relevant prompts and the absence …

Learning Camp, Language Of Instruction, And Education Outcomes: Evidence From A Field Experiment In Malawi, Hyuncheol Bryant. Kim, Kim

Research Collection School Of Economics

We conducted a randomized experiment to study the impacts of a summer learning camp and the language of instruction on education outcomes. The program, covering social studies and mathematics, provided additional high-quality learning time for 4th and 5th graders in Malawi. The program significantly increased test scores in social studies and mathematics (0.24–0.36 standard deviations). We find suggestive evidence that the impact on test scores in social studies was greater for students instructed in Chichewa, the local language, than for those instructed in English. However, we find no such evidence of differential impacts on test scores in mathematics by the …

Policy Evaluation With Nonlinear Trended Outcomes: Covid-19 Vaccination Rates In The United States, Lynn Bergeland Morgan, Peter C. B. Phillips, Donggyu Sul

Research Collection School Of Economics

This paper discusses pitfalls in two way fixed effects (TWFE) regressions when the outcome variables contain nonlinear and possibly stochastic trend components. If a policy change shifts trend paths of outcome variables, TWFE estimation can distort results and invalidate inference, especially in a context of evolving policy decisions. A robust solution is proposed by allowing for dynamic club membership empirically using a relative convergence test procedure. The determinants of respective club memberships are assessed by panel ordered logit regressions. The approach allows for policy evolution and shifts in outcomes according to a convergence cluster framework with transitions over time and …

Temporal Patterns Of New Product Introductions And Ipo Value: The Importance Of Recency, Dispersion, And Asymmetry, Suyun Mah, Rebecca J. Slotegraaf, Girish Mallapragada

Research Collection Lee Kong Chian School Of Business

A firm’s innovation activity is often judged by the number and type of new products it launches, but when these products are introduced may be equally important, especially before going public. This research investigates how the temporal pattern of new product introductions (NPIs) influences a firm’s initial public offering (IPO) value. The analysis uses data from 298 firms that went public between 2006 and 2023, and focuses on three patterns of timing: recency (how recently the latest product was launched before the IPO), dispersion (the degree to which NPIs before the IPO are spread out over time), and asymmetry (how …

Esg News, Future Cash Flows, And Firm Value, Francois Derrien, Philipp Krüger, Augustin Landier, Tianhao Yao

Research Collection Lee Kong Chian School Of Business

We investigate the expected consequences of negative environmental, social, and governance (ESG) news on firms' future profits. After learning about negative ESG news, analysts significantly downgrade their forecasts at short and longer horizons. Negative ESG news affects forecasts more strongly at longer horizons than other types of negative corporate news. The negative revisions of earnings forecasts following negative ESG news largely reflect expectations of lower future sales, rather than higher future costs. Quantitatively, forecast revisions can explain most of the negative impacts of ESG news on firm value. Analysts are correct to revise forecasts downward following negative ESG news.

Speculative Bubbles In The Recent Ai Boom: Nasdaq And The Magnificent Seven, Rerotlhe B. Basele, Peter C. B. Phillips, Shuping Shi

Research Collection School Of Economics

The recent artificial intelligence (AI) boom covers a period of rapid innovation and wide adoption of AI intelligence technologies across diverse industries. These developments have fueled an unprecedented frenzy in the Nasdaq, with AI-focused companies experiencing soaring stock prices that raise concerns about speculative bubbles and real-economy consequences. Against this background, this study investigates the formation of speculative bubbles in the Nasdaq stock market with a specific focus on the so-called Magnificent Seven (Mag-7) individual stocks during the AI boom, spanning the period from January 2017 to January 2025. We apply the real-time PSY bubble detection methodology of Phillips et …

Guiding Multiple Remote Users In Physical Tasks With Language-Driven Robotic Telepresence, Ruyi Li, Jingfei Guo, Xinyi Zhang, Xuji Zhang, Zeqing Li, Jiannan Li, Jiangtao Gong

Research Collection School Of Computing and Information Systems

Remote assistance through robotic telepresence could involve both control and memory challenges, particularly in one expert to multiple workers situation. In this work, we proposed a novelty language-driven interface to facilitate remote collaboration through telepresence robots. Through operations and maintenance expert interviews and a scenario simulation study, we identified key pain points in executing one-expert-multiple-workers remote guidance using the telepresence robot and proposed two design goals, which together consist of five sub-design goals with corresponding features. These features were integrated into a standard telepresence robot, resulting in the development of a Collaborative LLM-based Embodied Assistant Robot, named CLEAR Robot. A …

Implementing Slack-Free Custom Penalty Function For Qubo On Gate-Based Quantum Computers, Xin Wei Lee, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

Solving NP-hard constrained combinatorial optimization problems using quantum algorithms remains a challenging yet promising avenue toward quantum advantage. Variational Quantum Algorithms (VQAs), such as the Variational Quantum Eigensolver (VQE), typically require constrained problems to be reformulated as unconstrained ones using penalty methods. A common approach introduces slack variables and quadratic penalties in the QUBO formulation to handle inequality constraints. However, this leads to increased qubit requirements and often distorts the optimization landscape, making it harder to find high-quality feasible solutions. To address these issues, we explore a slack-free formulation that directly encodes inequality constraints using custom penalty functions, specifically the …

Robface: A Test Suite For Efficient Robustness Evaluation Of Face Recognition Systems, Ruihan Zhang, Jun Sun

Research Collection School Of Computing and Information Systems

Face recognition is a widely used authentication technology in practice, where robustness is required. It is thus essential to have an efficient and easy-to-use method for evaluating the robustness of (possibly third-party) trained face recognition systems. Existing approaches to evaluating the robustness of face recognition systems are either based on empirical evaluation (e.g., measuring attacking success rate using state-of-the-art attacking methods) or formal analysis (e.g., measuring the Lipschitz constant). While the former demands significant user efforts and expertise, the latter is extremely time-consuming. In pursuit of a comprehensive, efficient, easy-to-use, and scalable estimation of the robustness of face recognition systems, …