Digital Commons Network^™

Custom Permission Misconfigurations In Android: A Large-Scale Security Analysis, Rui Li, Wenrui Diao, Debin Gao

Research Collection School Of Computing and Information Systems

Android’s popularity is due to its openness and vast app ecosystem. Global developers can use Android Studio and rich Android APIs to create their apps. Within this ecosystem, Android permissions play a crucial role in managing access to resources, with system permissions controlled by system apps and custom permissions declared by third-party apps. However, the security of custom permissions has not received enough attention from the mobile security community, resulting in a lack of thorough evaluation of security practices for app developers using custom permissions. This study systematically evaluated the misconfiguration of custom permissions by Android app developers. It is …

Long-Tailed Out-Of-Distribution Detection Via Normalized Outlier Distribution Adaptation, Wenjun Miao, Guansong Pang, Jin Zheng, Xiao Bai

Research Collection School Of Computing and Information Systems

Onekeychallenge in Out-of-Distribution (OOD) detection is the absence of groundtruth OOD samples during training. One principled approach to address this issue is to use samples from external datasets as outliers (i.e., pseudo OOD samples) to train OOD detectors. However, we find empirically that the outlier samples often present a distribution shift compared to the true OOD samples, especially in LongTailed Recognition (LTR) scenarios, where ID classes are heavily imbalanced, i.e., the true OOD samples exhibit very different probability distribution to the head and tailed ID classes from the outliers. In this work, we propose a novel approach, namely normalized outlier …

Chain Of Preference Optimization: Improving Chain-Of-Thought Reasoning In Llms, Xuan Zhang, Chao Du, Tianyu Pang, Qian Liu, Wei Gao, Min Lin

Research Collection School Of Computing and Information Systems

The recent development of chain-of-thought (CoT) decoding has enabled large language models (LLMs) to generate explicit logical reasoning paths for complex problem-solving. However, research indicates that these paths are not always deliberate and optimal. The tree-of-thought (ToT) method employs tree-searching to extensively explore the reasoning space and find better reasoning paths that CoT decoding might overlook. This deliberation, however, comes at the cost of significantly increased inference complexity. In this work, we demonstrate that fine-tuning LLMs leveraging the search tree constructed by ToT allows CoT to achieve similar or better performance, thereby avoiding the substantial inference burden. This is achieved …

Gotcha ! This Model Uses My Code ! Evaluating Membership Leakage Risks In Code Models, Zhou Yang, Zhipeng Zhao, Chenyu Wang, Jieke Shi, Dongsum Kim, Donggyun Han, David Lo

Research Collection School Of Computing and Information Systems

Leveraging large-scale datasets from open-source projects and advances in large language models, recent progress has led to sophisticated code models for key software engineering tasks, such as program repair and code completion. These models are trained on data from various sources, including public open-source projects like GitHub and private, confidential code from companies, raising significant privacy concerns. This paper investigates a crucial but unexplored question: What is the risk of membership information leakage in code models? Membership leakage refers to the vulnerability where an attacker can infer whether a specific data point was part of the training dataset. We present …

User Acceptance Of Advice By Ai Agents: Expectation-System Fit Perspective, Jingyuan Cai, Fiona Fui-Hoon Nah

Research Collection School Of Computing and Information Systems

Algorithms have increasing influence on our daily decisions, especially when the recommendations are presented by human-like AI agents. This study applies the Theory of Effective Use to investigate how the fit between the user’s role expectation for an AI agent and the agent’s interaction style impacts AI advice adoption. We proposed a new concept termed Perceived Expectation-System Fit (PESF) and empirically examined its impact on user perceptions and advice acceptance. We found that low PESF reduces advice acceptance by diminishing cognitive and affective trust in the AI agent. Furthermore, increased algorithm transparency increases PESF's impact on decision-making. Our findings provide …

Shield-U: Safeguarding Traffic Sign Recognition Against Perturbation Attacks, Shengmin Xu, Jianfei Sun, Hangcheng Cao, Yulan Gao, Ziyang He, Cong Wu

Research Collection School Of Computing and Information Systems

Traffic sign recognition systems are crucial for the navigation and situation awareness of autonomous vehicles. They leverage deep learning technologies to swiftly and accurately identify traffic signs, even in the most challenging traffic environments. However, security researchers have uncovered a critical vulnerability in these systems: learning-based TSRs are particularly susceptible to physical-world perturbation attacks. Through subtle modifications (i.e., attaching well-designed patches on traffic signs), attackers can deceive the recognition system into making erroneous judgments, which can further lead to serious traffic accidents. Although several defense mechanisms have been proposed to enhance the security of sign recognition systems, these solutions generally …

Ohss: Optimizing Homomorphic Secret Sharing To Support Fast Matrix Multiplication, Shuguang Zhang, Jianli Bai, Kun Tu, Ziyue Yin, Chan Liu

Research Collection School Of Computing and Information Systems

Homomorphic Secret Sharing (HSS) has evolved as a state-of-the-art methodology for achieving secure two-party computation, synthesizing the advantages of secret sharing and homomorphic encryption. This amalgamation ensures minimal computational and communicational overhead, making it particularly adept at arithmetic operations. However, HSS faces challenges in scalability and efficiency when confronted with extensive matrix operations, including both matrix-vector and matrix-matrix multiplications, which are fundamental in numerous privacy-preserving computations, notably within the realm of privacy-preserving machine learning. In this research, we introduce Optimized Homomorphic Secret Sharing (OHSS), a refined version of HSS, crafted to address these limitations. Our contributions include enhancements to the …

Mvgamba : Unify 3d Content Generation As State Space Sequence Modeling, Xuanyu Yi, Zike Wu, Qiuhong Shen, Qingshan Xu, Pan Zhou, Joo-Hwee Lim, Shuicheng Yan, Xinchao Wang, Hanwang Zhang

Research Collection School Of Computing and Information Systems

Recent 3D large reconstruction models (LRMs) can generate high-quality 3D content in sub-seconds by integrating multi-view diffusion models with scalable multi-view reconstructors. Current works further leverage 3D Gaussian Splatting as 3D representation for improved visual quality and rendering efficiency. However, we observe that existing Gaussian reconstruction models often suffer from multi-view inconsistency and blurred textures. We attribute this to the compromise of multi-view information propagation in favor of adopting powerful yet computationally intensive architectures (e.g., Transformers). To address this issue, we introduce MVGamba, a general and lightweight Gaussian reconstruction model featuring a multi-view Gaussian reconstructor based on the RNN-like State …

Lova3 : Learning To Visual Question Answering, Asking And Assessment, Henry Hengyuan Zhao, Pan Zhou, Difei Gao, Bai Shou, Mike Zheng Shou

Research Collection School Of Computing and Information Systems

Question answering, asking, and assessment are three innate human traits crucial for understanding the world and acquiring knowledge. By enhancing these capabilities, humans can more effectively utilize data, leading to better comprehension and learning outcomes. Current Multimodal Large Language Models (MLLMs) primarily focus on question answering, often neglecting the full potential of questioning and assessment skills. Inspired by the human learning mechanism, we introduce LOVA3 , an innovative framework named “Learning tO Visual question Answering, Asking and Assessment,” designed to equip MLLMs with these additional capabilities. Our approach involves the creation of two supplementary training tasks GenQA and EvalQA, aiming …

An Integrative, Systematic Review Of The Situational Judgment Test Literature, Sven Kepes, Sheila K. Keener, Filip Lievens, Michael A. Mcdaniel

Research Collection Lee Kong Chian School Of Business

Situational judgment tests (SJTs) are popular assessment approaches that present scenarios describing situations that one may experience in a job. Due to its long history and cross-disciplinary nature, today’s SJT literature is quite fragmented. In this integrative review, we start by systematically taking stock and synthesizing the SJT literature from the different scientific disciplines via bibliometric techniques on 524 unique documents. We identify six literature clusters (i.e., SJTs in the medical sciences, SJTs in personnel selection, methodological issues and SJTs for specific constructs, SJTs to assess emotional intelligence and related constructs, technological advances in SJTs, SJTs for teacher assessment and …

Short-Term Personality Development And Early Career Success: Two Longitudinal Studies During The Post-Graduation Transition, Mary-Louise Hotze, Zihan Liu, Chu Chu, Erica Baranski, Kevin A. Hoff

Research Collection Lee Kong Chian School Of Business

Objective: Investigate short-term personality development during the post-graduation transition. Background: Prior research indicates that long-term personality development matters for employment outcomes. However, this evidence is primarily limited to multi-year longitudinal studies. This research switches the focus to personality changes during a shorter, impactful life transition. Method: We examined how short-term personality development during the 14-month post-graduation transition relates to early career outcomes among two diverse samples of graduates from universities (N = 816) and community colleges (N = 567). We used latent growth curve models to examine associations between career outcomes measured 14 months after graduation with initial personality levels …

Automating Maritime Risk Data Collection And Identification Leveraging Large Language Models, Donghao Huang, Xiuju Fu, Xiaofeng Yin, Haibo Pen, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

Maritime risk research is crucial yet challenging for improving safety, efficiency, and sustainability in maritime operations. This paper presents an innovative method for automating the collection and identification of risk data related to global maritime risks from news sources, addressing the limitations of traditional manual methods. To evaluate the proposed method, different learning-based models, including conventional machine learning approaches and advanced Large Language Models (LLMs) such as GPT-4 and LLaMA-3.1, are comprehensively studied for comparison. In addition, not only do we use popular evaluation metrics to assess the proposed method, but we also introduce a new evaluation metric, called the …

Divlog: Log Parsing With Prompt Enhanced In-Context Learning, Junjielong Xu, Ruichun Yang, Yintong Huo, Chengyu Zhang, Pinjia He

Research Collection School Of Computing and Information Systems

Log parsing, which involves log template extraction from semistructured logs to produce structured logs, is the first and the most critical step in automated log analysis. However, current log parsers suffer from limited effectiveness for two reasons. First, traditional data-driven log parsers solely rely on heuristics or handcrafted features designed by domain experts, which may not consistently perform well on logs from diverse systems. Second, existing supervised log parsers require model tuning, which is often limited to fixed training samples and causes sub-optimal performance across the entire log source. To address this limitation, we propose DivLog, an effective log parsing …

Collaboration! Towards Robust Neural Methods For Routing Problems, Jianan Zhou, Yaoxin Wu, Zhiguang Cao, Wen Song, Jie Zhang, Zhiqi Shen

Research Collection School Of Computing and Information Systems

Despite enjoying desirable efficiency and reduced reliance on domain expertise, existing neural methods for vehicle routing problems (VRPs) suffer from severe robustness issues – their performance significantly deteriorates on clean instances with crafted perturbations. To enhance robustness, we propose an ensemble-based Collaborative Neural Framework (CNF) w.r.t. the defense of neural VRP methods, which is crucial yet underexplored in the literature. Given a neural VRP method, we adversarially train multiple models in a collaborative manner to synergistically promote robustness against attacks, while boosting standard generalization on clean instances. A neural router is designed to adeptly distribute training instances among models, enhancing …

Here, There, And Elsewhere: Ethnicity, Identity, And Global Orientation At An Indian International School In Singapore, Emma Alexandra Grimley, Orlando Woods, Lily Kong

Research Collection College of Integrative Studies

International schools are somewhat ‘place-less’ in that their denationalised educational systems and nationally diverse student bodies are typically removed from the physical context in which each school is located. However, this placeless internationalism is complicated by international schools that also affiliate themselves with a national system or enrol a significant number of students who aspire to remain in the ‘host’ country. This paper develops the example of the Global Indian International School in Singapore to illustrate how the feeling of place is impacted by its dual orientations as both ‘Global’ and ‘Indian.’ The school attempts to (re)create an Indian schooling …

Safety Through Feedback In Constrained Rl, Shashank Reddy Chirra, Pradeep Varakantham, Praveen Paruchuri

Research Collection School Of Computing and Information Systems

In safety-critical RL settings, the inclusion of an additional cost function is often favoured over the arduous task of modifying the reward function to ensure the agent's safe behaviour. However, designing or evaluating such a cost function can be prohibitively expensive. For instance, in the domain of self-driving, designing a cost function that encompasses all unsafe behaviours (e.g., aggressive lane changes, risky overtakes) is inherently complex, it must also consider all the actors present in the scene making it expensive to evaluate. In such scenarios, the cost function can be learned from feedback collected offline in between training rounds. This …

Sorry Not Sorry: Presentational Strategies And The Electoral Punishment Of Corruption, Dean C. Dulay, Seulki Lee

Research Collection School of Social Sciences

A growing literature has explored various factors that hamper the electoral punishment of corruption. Most studies have focused on how voters react to a corruption allegation, but this focus leaves out an important, common aspect of corruption allegations that voters also encounter: politicians' blame avoidance strategies. This study examines how politicians' presentational strategies in response to corruption allegations affect voter sanctioning. Employing an online survey experiment on a sample of 3531 U.S. citizens, we find that politicians' action-oriented strategies, such as denying allegations, acknowledging a problem but denying responsibility, or acknowledging a problem and taking responsibility, are more effective than …

(In)Visible China: Understanding Chinese Global Orders, Hassan Karrar, William A. Callahan, Carwyn Morris, Stephen Whiteman

Research Collection School of Social Sciences

Where is China going? What does its alternative global order look like? We hear a lot about China’s grand projects like the Belt and Road Initiative, but how are they experienced on the ground in Africa, South America, and Asia?The Chinese Global Orders project brings together twenty-two scholars from five continents to explore these questions. As these four commentaries show, it seeks to pluralize the discussion by exploring “Chinese” beyond the PRC nation-state, “Global” as a space beyond the international, and “Orders” as a plural set of norms.The project seeks to do more than just describe Global China’s material impact, …

Reevo: Large Language Models As Hyper-Heuristics With Reflective Evolution, Haoran Ye, Jiarui Wang, Zhiguang Cao, Federico Berto, Chuanbo Hua, Haeyeon Kim, Jinkyoo Park, Guojie Song

Research Collection School Of Computing and Information Systems

The omnipresence of NP-hard combinatorial optimization problems (COPs) compels domain experts to engage in trial-and-error heuristic design process. The long-standing endeavor of design automation has gained new momentum with the rise of large language models (LLMs). This paper introduces Language Hyper-Heuristics (LHHs), an emerging variant of Hyper-Heuristics that leverages LLMs for heuristic generation, featuring minimal manual intervention and open-ended heuristic spaces. To empower LHHs, we present Reflective Evolution (ReEvo), a generic searching framework that emulates the reflective design approach of human experts while far surpassing human capabilities with its scalable LLM inference, Internet-scale domain knowledge, and powerful evolutionary search. Evaluations …

Disputing Personal Data In The Eu-China Comprehensive Agreement On Investment, Mark Mclaughlin

Research Collection Yong Pung How School Of Law

This chapter analyses the emerging data realms in China and the European Union against the backdrop of the Comprehensive Agreement on Investment (CAI). It examines the link between data protection and investment flows and undertakes a comparative analysis of the PIPL and GDPR. Moreover, this chapter will also analyse the Digital Silk Road in promoting China’s model of data sovereignty. While early trade and investment agreements did not consider data relevant for the regulation of cross-border commerce, modern treaties are increasingly cognisant of rules for data protection. As such, the data-related provisions of the CAI will be placed in the …

Converting Vocal Performances Into Sheet Music Leveraging Large Language Models, Jinjing Jiang, Nicole Teo, Haibo Pen, Seng-Beng Ho, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

Advanced natural language processing (NLP) models are increasingly applied in music composition and performance, particularly for generating vocal melodies and simulating singing voices. While NLP techniques have been effective in analyzing vocal performance data to assess quality and style, the automatic transcription of vocal performances into sheet music remains a significant challenge. Manual transcription tools often fall short due to the intricate dynamics of vocal expression. This study tackles the automation of vocal performance transcription into sheet music using innovative techniques, including large language models (LLMs). We propose a method to translate vocal audio input into display-ready sheet music effectively. …

Sampdetox : Black-Box Backdoor Defense Via Perturbation-Based Sample Detoxification, Yanxin Yang, Chentao Jia, Dengke Yan, Ming Hu, Tianlin Li, Xiaofei Xie, Xian Wei, Mingsong Chen

Research Collection School Of Computing and Information Systems

The advancement of Machine Learning has enabled the widespread deployment of Machine Learning as a Service (MLaaS) applications. However, the untrustworthy nature of third-party ML services poses backdoor threats. Existing defenses in MLaaS are limited by their reliance on training samples or white-box model analysis, highlighting the need for a black-box backdoor purification method. In our paper, we attempt to use diffusion models for purification by introducing noise in a forward diffusion process to destroy backdoors and recover clean samples through a reverse generative process. However, since a higher noise also destroys the semantics of the original samples, it still …

Sprinql : Sub-Optimal Demonstrations Driven Offline Imitation Learning, Minh Huy Hoang, Tien Mai, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

We focus on offline imitation learning (IL), which aims to mimic an expert's behavior using demonstrations without any interaction with the environment. One of the main challenges in offline IL is the limited support of expert demonstrations, which typically cover only a small fraction of the state-action space. While it may not be feasible to obtain numerous expert demonstrations, it is often possible to gather a larger set of sub-optimal demonstrations. For example, in treatment optimization problems, there are varying levels of doctor treatments available for different chronic conditions. These range from treatment specialists and experienced general practitioners to less …

Self-Supervised Fine-Tuning For Neural Expert Finding, Budhitama Subagdja, Dan Sanchari, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Expert finding systems allow ones to find individuals who have expertise in specific fields or domains. Traditional expert finding are mostly based on topic modeling or keyword search methods that are limited in their capability to encode contextual knowledge from natural language. To address the limitation, this paper presents Neural Expert Finder (NEF), a novel method that takes a transfer learning approach based on transformer encoder networks to leverage the rich seman-tic and syntactic patterns of language encoded in pre-trained language models (PLMs). We propose a self-supervised learning approach utilizing contrastive training using both positive and automatically generated negative samples …

Replay-And-Forget-Free Graph Class-Incremental Learning: A Task Profiling And Prompting Approach, Chaoxi Niu, Guansong Pang, Ling Chen, Bing Liu

Research Collection School Of Computing and Information Systems

Class-incremental learning (CIL) aims to continually learn a sequence of tasks, with each task consisting of a set of unique classes. Graph CIL (GCIL) follows the same setting but needs to deal with graph tasks (e.g., node classification in a graph). The key characteristic of CIL lies in the absence of task identifiers (IDs) during inference, which causes a significant challenge in separating classes from different tasks (i.e., inter-task class separation). Being able to accurately predict the task IDs can help address this issue, but it is a challenging problem. In this paper, we show theoretically that accurate task ID …

Gtree: Gpu-Friendly Privacy-Preserving Decision Tree Training And Inference, Qifan Wang, Shujie Cui, Lei Zhou, Ye Dong, Jianli Bai, Yun Sing Koh, Giovanni Russello

Research Collection School Of Computing and Information Systems

Outsourcing Decision tree (DT) training and inference to cloud platforms raises privacy concerns. Recent Secure Multi-Party Computation (MPC)-based methods are hindered by heavy overhead. Few recent studies explored GPUs to improve MPC-protected deep learning, yet integrating GPUs into MPC-protected DT with massive data-dependent operations remains challenging, raising question: can MPC-protected DT training and inference fully leverage GPUs for optimal performance?We present GTree, the first scheme that exploits GPU to accelerate MPC-protected secure DT training and inference. GTree is built across 3 parties who jointly perform DT training and inference with GPUs. GTree is secure against semi-honest adversaries, ensuring that no …

Lilac: Log Parsing Using Llms With Adaptive Parsing Cache, Zhihan Jiang, Jinyang Liu, Zhuangbin Chen, Yichen Li, Junjie Huang, Yintong Huo, Pinjia He, Jiazhen Gu, R. Michael Lyu

Research Collection School Of Computing and Information Systems

Log parsing transforms log messages into structured formats, serving as the prerequisite step for various log analysis tasks. Although a variety of log parsing approaches have been proposed, their performance on complicated log data remains compromised due to the use of human-crafted rules or learning-based models with limited training data. The recent emergence of powerful large language models (LLMs) demonstrates their vast pre-trained knowledge related to code and logging, making it promising to apply LLMs for log parsing. However, their lack of specialized log parsing capabilities currently hinders their parsing accuracy. Moreover, the inherent inconsistent answers, as well as the …

From A Timeline Contact Graph To Close Contact Tracing And Infection Diffusion Intervention, Yipeng Zhang, Zhifeng Bao, Yuchen Li, Baihua Zheng, Xiaoli Wang

Research Collection School Of Computing and Information Systems

This paper proposes a novel graph structure to address the problems of information spreading in a real-world, frequently updating graph, with two main contributions at hand: accurately tracing infection diffusion according to fine-grained user movements and finding vulnerable vertices under the virus immunization scenario to mitigate infection diffusion. Unlike previous work that primarily predicts the long-term epidemic trend at the census level, this study aims to intervene in the short-term at the individual level. Therefore, two downstream tasks are formulated to illustrate practicalities: Epidemic Mitigating in Public Area problem (EMA) and Epidemic Maximized Spread in Public Area problem (ESA), where …

Optimizing Open Research: Data And Code Sharing At S-Lab, Chen Change Loy, Geong Sen Poh, Chee Guan Koh, Moi Moi Siew, Jin Boon Ng

Singapore Open Research Conference 2024

Lightning talk “Optimizing Open Research - Data and Code Sharing at S-Lab” by Winner of the Singapore Open Research Awards 2024, Professor Chen Change LOY from Nanyang Technological University.

S-Lab for Advanced Intelligence (S-Lab) is committed to advancing transparency, reproducibility, and collaboration within the scientific community. By sharing data, demos, and codes on publicly discoverable platforms such as DR-NTU (Data), OpenMMLab, OpenXLab, GitHub, and Hugging Face, we make our codes and datasets open and reusable. We believe that by making open data and code FAIR - Findable, Accessible, Interoperable, and Reusable, they can be scrutinised, and reused by fellow researchers …

Rediscovering Publicly Available Single-Cell Data With The Disco Platform, Jinmiao Chen

Singapore Open Research Conference 2024

Since its inception in 2009, single-cell RNA-seq techniques have evolved, increasing throughput and reducing costs. With a growing number of published studies, efficient data retrieval is crucial. DISCO was created as a comprehensive database of single-cell RNA-seq data, enabling exploration of cell types and gene expressions in various tissues. Now, DISCO hosts over 100 million single-cell profiles from 16,734 samples, reflecting a fivefold increase since its first version. We have curated metadata, categorized samples, and refined cell type annotations using a harmonized reference. DISCO platform provides online tools for data integration, cell type annotation, projecting query dataset to atlases, and …