Digital Commons Network^™

General Test-Time Backdoor Detection In Split Neural Network-Based Vertical Federated Learning, Shunjie Yuan, Xinghua Li, Xuelin Cao, Haiyan Zhang, Robert H. Deng

Research Collection School Of Computing and Information Systems

As a new distributed machine learning framework, vertical federated learning (VFL) has been widely applied in the industry. However, recent studies have demonstrated that VFL faces serious challenges from backdoor attacks, which significantly hinder its further development. Although a few studies have focused on defending against VFL backdoor attacks, these defenses either do not consider the latest attack methods or show limited effectiveness. Moreover, most existing backdoor defense efforts primarily focus on backdoor attacks in horizontal federated learning (HFL) and centralized learning. Due to the unique architecture of VFL models, these methods cannot be directly applied to backdoor defense in …

Fl-Cdf: Collaborative Defense Framework For Backdoor Mitigation In Federated Learning, Haiyan Zhang, Xinghua Li, Yinbin Miao, Shunjie Yuan, Mengyao Zhu, Ximeng Liu, Robert H. Deng

Research Collection School Of Computing and Information Systems

Federated learning (FL) is vulnerable to backdoor attacks due to its distributed nature. Existing unilateral defense mechanisms often fail against persistent attack strategies, primarily due to their limited perspectives. To address the challenge of model misclassification on the server side caused by overlooked model similarity drift, and gradient misjudgment on the client side caused by semantic learning imbalances across classes, this paper proposes a collaborative defense framework for federated learning, termed FL-CDF. FL-CDF establishes an end-to-end defense through a bidirectional client-server collaboration mechanism. Specifically: (1) On the client side, an adversarial perturbation-based malicious neuron detection module is introduced. This module …

Genscore: Agent-Based Short-Answer Question Generation And Scoring In Software Engineering Courses, Nguyen Binh Duong Ta, Lwin Khin Shar

Research Collection School Of Computing and Information Systems

Short-answer questions are commonly used in educational assessments, as they are often viewed as a more effective way than multiple-choice questions to determine whether students have achieved the intended learning outcomes. However, manually creating appropriate questions targeting different cognitive levels such as those defined by the Bloom’s Taxonomy, and grading text answers from students are not trivial tasks for instructors. Existing work on auto-question generation and scoring in computing education typically targets coding-based questions. However, in software engineering courses, assessments can extend beyond coding to understanding of processes, DevOps methodologies, system design, etc. This work aims to address the dual …

Scalable Graph Indexing Using Gpus For Approximate Nearest Neighbor Search, Zhonggen Li, Xiangyu Ke, Yifan Zhu, Bocheng Yu, Baihua Zheng, Yunjun Gao

Research Collection School Of Computing and Information Systems

Approximate nearest neighbor search (ANNS) in high-dimensional vector spaces has a wide range of real-world applications. Numerous methods have been proposed to handle ANNS efficiently, while graph-based indexes have gained prominence due to their high accuracy and efficiency. However, the indexing overhead of graph-based indexes remains substantial. With exponential growth in data volume and increasing demands for dynamic index adjustments, this overhead continues to escalate, posing a critical challenge.In this paper, we introduce Tagore, a fasT library accelerated by GPUs for graph indexing, which has powerful capabilities of constructing refinement-based graph indexes such as NSG and Vamana. We first introduce …

Pilot-C: Physics-Informed Low-Distortion Optimal Trajectory Compression, Kefei Wu, Baihua Zheng, Weiwei Sun

Research Collection School Of Computing and Information Systems

Location-aware devices continuously generate massive volumes of trajectory data, creating demand for efficient compression. Line simplification is a common solution but typically assumes 2D trajectories and ignores time synchronization and motion continuity. We propose PILOT-C, a novel trajectory compression framework that integrates frequency-domain physics modeling with error-bounded optimization. Unlike existing line simplification methods, PILOT-C supports trajectories in arbitrary dimensions, including 3D, by compressing each spatial axis independently. Evaluated on four real-world datasets, PILOT-C achieves superior performance across multiple dimensions. In terms of compression ratio, PILOT-C outperforms CISED-W, the current state-of-the-art SED-based line simplification algorithm, by an average of 19.2%. For …

Contx: Scene Context Prediction Via Context Bank And Layout Perception, Jingxin Liang, Yangyang Xu, Haorui Song, Yuan Lu, Yuhui Deng, Yiyi Long, Yan Huang, Shengxin Liu, Jianbo Jiao, Shengfeng He

Research Collection School Of Computing and Information Systems

Scene context prediction, which seeks to infer unknown contextual information from isolated object properties, currently faces limitations due to predominant reliance on pixel-wise supervision that overlooks real-world context priors. To address this, we present ContX, a context-prior-driven, coarse-to-fine model. ContX distinctively integrates explicit linguistic-contextual knowledge in two key ways. First, it proposes a linguistic guided context bank, leveraging linguistic-statistical contextual data to guide the rationality of segmentation shapes and foster meaningful inter-class contextual interactions. Second, ContX augments contextual comprehension by correlating layouts with linguistic descriptions, enhancing layout perception through a multi-modal strategy. Comprehensive experiments demonstrate ContX's superiority and versatility, outperforming …

A Learning‑Augmented Dynamic Programming Approach For Orienteering Problem With Time Windows, Guansheng Peng, Lining Xing, Fuyan Song Ma, Aldy Gunawan, Aldy Gunawan

Research Collection School Of Computing and Information Systems

Recent years have witnessed a surge of interest in solving combinatorial optimization problems (COPs) using machine learning techniques. Motivated by this trend, we propose a learning-augmented exact approach for tackling an NP-hard COP, the Orienteering Problem with Time Windows, which aims to maximize the total score collected by visiting a subset of vertices in a graph within their time windows. Traditional exact algorithms rely heavily on domain expertise and meticulous design, making it hard to achieve further improvements. By leveraging deep learning models to learn effective relaxations of problem restrictions from data, our approach enables significant performance gains in an …

Griffin: Effective Token Alignment For Faster Speculative Decoding, Shijing Hu, Jingyang Li, Xingyu Xie, Zhihui Lu, Kim-Chuan Toh, Pan Zhou

Research Collection School Of Computing and Information Systems

Speculative decoding accelerates inference in large language models (LLMs) by generating multiple draft tokens simultaneously. However, existing methods often struggle with token misalignment between the training and decoding phases, limiting their performance. To address this, we propose GRIFFIN, a novel framework that incorporates a token-alignable training strategy and a token-alignable draft model to mitigate misalignment. The training strategy employs a loss masking mechanism to exclude highly misaligned tokens during training, preventing them from negatively impacting the draft model’s optimization. The token-alignable draft model introduces input tokens to correct inconsistencies in generated features. Experiments on LLaMA, Vicuna, Qwen and Mixtral models …

Evaluating Defi Vulnerabilities: The Role Of Bug Bounty Programs On Defi Software Supply Chain, Ping Fan Ke, Yi Meng Lau, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Decentralized finance (DeFi), powered by blockchain technology, enables peer-to-peer financial transactions without intermediaries. Despite rapid adoption, DeFi attracts malicious actors exploiting vulnerabilities. To mitigate risks, we propose a framework assessing entry points in the DeFi software supply chain: smart contracts, oracles/third-party feeds, user interfaces, off-chain storage, and crypto wallets. Applying this framework, we evaluate whether industry solutions—particularly bug bounty programs—adequately address these gaps. Our preliminary analysis indicates that most programs cover smart contract vulnerabilities (85.7%), followed by user interface issues (21.3%) and crypto wallet loopholes (11.9%). However, third-party risks, such as oracle feeds, are frequently deemed out of scope. This …

A Socio-Technical Analysis Of Market Reactions On Meme Coins: Trump’S Presidential Effect, Ping Fan Ke, Yi Meng Lau

Research Collection School Of Computing and Information Systems

Meme coins are a unique type of cryptocurrency whose value is shaped by internet culture and viral trends. This study introduces a socio-technical research model to examine key factors influencing meme coin dynamics and applies it to analyze market reactions to Donald Trump’s 2024 U.S. presidential election victory and inauguration, focusing on the $TRUMP meme coin and other politics-related meme coins, known as PolitiFi. Using a mixed-methods approach, we analyze publicly available news, social media activity, and marketplace data to investigate the interaction between social engagement and technical infrastructure. Econometric analysis shows that Trump-related events triggered short-term price surges, increased …

No Experts, No Problem: Avoidance Learning From Bad Demonstrations, Minh Huy Hoang, Tien Mai, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

This paper addresses the problem of learning avoidance behavior within the context of offline imitation learning. In contrast to conventional methodologies that prioritize the replication of expert or near-expert demonstrations, our work investigates a setting where expert (or desirable) data is absent, and the objective is to learn to eschew undesirable actions by leveraging demonstrations of such behavior (i.e., learning from negative examples).To address this challenge, we propose a novel training objective grounded in the maximum entropy principle. We further characterize the fundamental properties of this objective function, reformulating the learning process as a cooperative inverse Q-learning task. Moreover, we …

The Rise Of Parameter Specialization For Knowledge Storage In Large Language Models, Yihuai Hong, Yiran Zhao, Wei Tang, Yang Deng, Yu Rong, Wenxuan Zhang

Research Collection School Of Computing and Information Systems

Over time, a growing wave of large language models from various series has been introduced to the community. Researchers are striving to maximize the performance of language models with constrained parameter sizes. However, from a microscopic perspective, there has been limited research on how to better store knowledge in model parameters, particularly within MLPs, to enable more effective utilization of this knowledge by the model. In this work, we analyze twenty publicly available open-source large language models to investigate the relationship between their strong performance and the way knowledge is stored in their corresponding MLP parameters. Our findings reveal that …

A Partition Cover Approach To Tokenization, Jia Peng Lim, Shawn Tan, Davin Choo, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Tokenization is the process of encoding strings into tokens of a fixed vocabulary size, and is widely utilized in Natural Language Processing applications. The leading tokenization algorithm today is Byte Pair Encoding (BPE), which formulates the tokenization problem as a compression problem and tackles it by performing sequences of merges. In this work, we formulate tokenization as an optimization objective, show that it is NP-hard via a simple reduction from vertex cover, and propose a polynomial-time greedy algorithm GreedTok. Our formulation naturally relaxes to the well-studied weighted maximum coverage problem which has a simple -approximation algorithm GreedWMC. Through empirical evaluations …

Diseño Visual, Identidad De Género Y Diversidad Cultural En La Animación Contemporánea: El Caso De Raya And The Last Dragon, Elisabet Fonts González

GDI. Revista de investigación de Género, Diseño e Innovación

En los últimos años, la animación ha evolucionado hacia representaciones más inclusivas de género y diversidad cultural. Raya and the Last Dragon (López Estrada & Hall, 2021) destaca como un caso significativo de esta transformación, integrando elementos visuales, narrativos y simbólicos que reconfiguran los arquetipos femeninos tradicionales. Este estudio adopta un enfoque cualitativo centrado en el análisis visual, narrativo y simbólico de los personajes Raya, Namaari y Sisu. Basándose en fuentes primarias del proceso creativo y marcos teóricos de la animación y los estudios de género (Furniss, 2017; Lauretis, 1987; Wells, 1998), presta especial atención al diseño de personajes, la …

Elena Asins Y Las Afueras Del Canon: Animación Computacional Y Resistencia, Maria Mar Garrido Román

GDI. Revista de investigación de Género, Diseño e Innovación

Este artículo examina las animaciones generadas por ordenador producidas por Elena Asins, analizando cómo su práctica artística moviliza el pensamiento lógico-matemático, la programación y la experimentación visual. A través de una revisión de su metodología, contexto de producción y resultados formales, el estudio explora la incorporación de procesos algorítmicos en su obra, que generan imágenes con extensión temporal y la consolidan como una figura clave en la historia del arte digital y la animación experimental en España.

La investigación se basa en el análisis de fuentes primarias y, con el objetivo de situar su producción en un marco internacional, establece …

Entre La Sombra Y El Lienzo: Clea Dessendre Como Modelo De Personaje Secundario Complejo, Lydia Huijbregts Jaen, Antonio Horno López

GDI. Revista de investigación de Género, Diseño e Innovación

Introducción: Este artículo analiza a Clea Dessendre en Clair Obscure: Expedition 33, explorando su versión real y la pintada en el lienzo, y su impacto en la narrativa del juego. Metodología: Se aplicó un análisis narrativo, psicológico y ludológico, integrando teorías de duelo (Kübler-Ross), socialización (Baumrind) y comunicación (DiSC) vinculadas con la jugabilidad. Resultados: Clea-Real encarna disciplina y perfeccionismo; Clea-Pintada, una proyección maternal. El gameplay conecta su psicología con la experiencia del jugador. Discusión: Las identidades paralelas muestran cómo traumas y expectativas moldean personajes complejos. Conclusiones: Clea evidencia cómo la narrativa y la mecánica se fusionan para crear …

Una Animación Propia. Discurso Emancipador Desde El Cine De Animación Independiente, Elisa Martínez, Damià Jordà

GDI. Revista de investigación de Género, Diseño e Innovación

Introducción: A pesar de la temprana incorporación de las mujeres a la industria de la animación, sus roles fueron históricamente relegados a labores mecánicas, limitando su capacidad de decisión creativa. Este artículo analiza cómo el cine de animación independiente del siglo XX funcionó como un espacio esencial para las directoras que buscaban un control artístico que permitiera desarrollar discursos emancipadores. Se parte de la hipótesis de que el circuito independiente propició que las animadoras desarrollaran técnicas y narrativas alternativas que rompieron con los cánones plásticos y los preceptos ideológicos dominantes en la industria. Metodología: Mediante una metodología cualitativa, …

Animación Por Mujeres Colombianas: La Potencia Expresiva Del Trabajo Hecho A Mano, Daniela Posada Sarmiento

GDI. Revista de investigación de Género, Diseño e Innovación

Este artículo busca situar el trabajo de tres mujeres animadoras colombianas dentro del campo de investigación sobre el género y la animación, evidenciando la escasa presencia de sus aportes en la investigación académica. Se pretende demostrar la hipótesis que sostiene que: existen obras de animación contemporánea desarrolladas por mujeres colombianas que contienen aportes formales, conceptuales, estéticos y poéticos significativos para la investigación en torno a la animación. En primer lugar, se desarrolla un Estado de la cuestión con enfoque crítico, que permite identificar cómo se ha ignorado la participación de mujeres colombianas en los estudios sobre animación. Posteriormente, se caracterizan …

Representando El Buen Queer-Er: Otras Miradas Para Romper La Cisheteronorma En La Animación Infantil-Juvenil, Delicia Aguado Peláez, Patricia Martínez García

GDI. Revista de investigación de Género, Diseño e Innovación

Este artículo explora la ruptura de los estereotipos de género y la representación de la diversidad en series de animación infantil y juvenil creadas por mujeres y disidencias. Partiendo de un análisis de contenido cualitativo desde una perspectiva interseccional, examinamos la construcción de personajes, las dinámicas sexo-afectivas y las relaciones de poder que se encuentran en cuatro producciones: Star vs. Evil Forces (Daron Nefcy), Steven Universe (Rebeca Sugar), She-Ra and the Princesses of Power (ND Stevenson) y The Owl House (Dana Terrace). Todas ellas comparten una serie de características: ofrecen modelos alternativos de feminidad y masculinidad, más allá de …

Colaboración, Discurso Y Técnicas: La Resistencia Simbólica En El Sueño De La Sultana (Isabel Herguera, 2023), Nerea Cuenca-Orellana

GDI. Revista de investigación de Género, Diseño e Innovación

La película El sueño de la sultana (Isabel Herguera, 2023) reinterpreta el cuento utópico homónimo de Rokeya Sakhawat Hossain (1905) realizando una exploración visual que combina animación, archivo y testimonio. El presente trabajo propone un análisis de la obra desde cuatro puntos clave e interrelacionados: la autoría colaborativa y femenina, los discursos visuales, los lenguajes y técnicas, y las formas de resistencia simbólica con el objetivo principal de establecerla como un caso práctico de diseño feminista contemporáneo.

En primer lugar, se examina el proceso de creación de la película como práctica colaborativa transnacional, donde la animación se convierte en un …

Instance-Level Video Depth In Groups Beyond Occlusions, Yuan Liang, Yang Zhou, Ziming Sun, Tianyi Xiang, Guiqing Li, Shengfeng He

Research Collection School Of Computing and Information Systems

Depth estimation in dynamic, multi-object scenes remains a major challenge, especially under severe occlusions. Existing monocular models, including foundation models, struggle with instance-wise depth consistency due to their reliance on global regression. We tackle this problem from two key aspects: data and methodology. First, we introduce the Group Instance Depth (GID) dataset, the first large-scale video depth dataset with instance-level annotations, featuring 101,500 frames from real-world activity scenes. GID bridges the gap between synthetic and real-world depth data by providing high-fidelity depth supervision for multi-object interactions. Second, we propose InstanceDepth, the first occlusion-aware depth estimation framework for multi-object environments. Our …

Robust Hallucination Detection In Llms Via Adaptive Token Selection, Mengjia Niu, Hamed Haddadi, Guansong Pang

Research Collection School Of Computing and Information Systems

Hallucinations in large language models (LLMs) pose significant safety concerns that impede their broader deployment. Recent research in hallucination detection has demonstrated that LLMs’ internal representations contain truthfulness hints, which can be harnessed for detector training. However, the performance of these detectors is heavily dependent on the internal representations of predetermined tokens, fluctuating considerably when working on free-form generations with varying lengths and sparse distributions of hallucinated entities. To address this, we propose HaMI, a novel approach that enables robust detection of hallucinations through adaptive selection and learning of critical tokens that are most indicative of hallucinations. We achieve this …

Semi‑Supervised Graph Anomaly Detection Via Robust Homophily Learning, Guoguo Ai, Hezhe Qiao, Hui Yan, Guansong Pang

Research Collection School Of Computing and Information Systems

Current semi-supervised graph anomaly detection (GAD) methods utilizes a small set of labeled normal nodes to identify abnormal nodes from a large set of unlabeled nodes in a graph. These methods posit that 1) normal nodes share a similar level of homophily and 2) the labeled normal nodes can well represent the homophily patterns in the entire normal class. However, this assumption often does not hold well since normal nodes in a graph can exhibit diverse homophily in real-world GAD datasets. In this paper, we propose RHO, namely Robust Homophily Learning, to adaptively learn such homophily patterns. RHO consists of …

Coresets For Clustering Under Stochastic Noise, Lingxiao Huang, Zhize Li, Nisheeth K. Vishnoi, Runkai Yang, Haoyu Zhao

Research Collection School Of Computing and Information Systems

We study the problem of constructing coresets for $(k, z)$-clustering when the input dataset is corrupted by stochastic noise drawn from a known distribution. In this setting, evaluating the quality of a coreset is inherently challenging, as the true underlying dataset is unobserved. To address this, we investigate coreset construction using surrogate error metrics that are tractable and provably related to the true clustering cost. We analyze a traditional metric from prior work and introduce a new error metric that more closely aligns with the true cost. Although our metric is defined independently of the noise distribution, it enables approximation …

Design Principles For Customer‑Engaging Digital Service Systems: An Action Research Study, Keng Siau, Xiaofeng Chen, Xin Tan

Research Collection School Of Computing and Information Systems

Digital services represent a business approach employed by organizations to operate in the digital environment. However, systematic development guidelines for developing quality digital service systems are lacking in the literature. The authors identified four general challenges for developing and implementing customer-engaging digital service systems (CEDSS). By employing the method of canonical action research in a digital service system project, they derived 10 design principles for developing high-quality CEDSS. They empirically evaluated the design principles in the development project and through follow-up focus group sessions. The design principles provide applicable and actionable guidelines for the development of CEDSS.

Accuracy-Enabling Differential Privacy-Preserving Truth Discovery, Man Zhang, Xinghua Li, Yinbin Miao, Bin Luo, Siqi Ma, Robert H. Deng

Research Collection School Of Computing and Information Systems

Perturbation-based privacy-preserving truth discovery requires the Service Provider (SP) to calculate the truthful aggregation result from perturbed data of the Data Sources (DSs), which inevitably damages the aggregation accuracy due to perturbation noise added in the data. Thus, the existing works attempt to relieve the perturbation errors by reducing noise amounts or adjusting aggregation weights of DSs. However, the former sacrifices DSs’ privacy preservation and the latter has the limited accuracy recovery performance. Aiming at it, we propose an accuracy-enabling differential privacy-preserving truth discovery consisting of an independence-guaranteed data perturbation module and a progressive-private noise elimination module. Specifically, in the …

Bias Testing And Mitigation In Llm-Based Code Generation, Dong Huang, Jie M. Zhang, Qingwen Bu, Xiaofei Xie, Junjie Chen, Heming Cui

Research Collection School Of Computing and Information Systems

As the adoption of LLMs becomes more widespread in software coding ecosystems, a pressing issue has emerged: does the generated code contain social bias and unfairness, such as those related to age, gender, and race? This issue concerns the integrity, fairness, and ethical foundation of software applications that depend on the code generated by these models but are underexplored in the literature. This paper presents a novel bias testing framework that is specifically designed for code generation tasks. Based on this framework, we conduct an extensive empirical study on the biases in code generated by five widely studied LLMs (i.e., …

Island-Based Evolutionary Computation With Diverse Surrogates And Adaptive Knowledge Transfer For High-Dimensional Data-Driven Optimization, Xianrong Zhang, Yuejiao Gong, Zhiguang Cao, Jun Zhang

Research Collection School Of Computing and Information Systems

In recent years, there has been a growing interest in data-driven evolutionary algorithms (DDEAs) employing surrogate models to approximate the objective functions with limited data. However, current DDEAs are primarily designed for lower-dimensional problems and their performance drops significantly when applied to large-scale optimization problems (LSOPs). To address the challenge, this paper proposes an offline DDEA named DSKT-DDEA. DSKT-DDEA leverages multiple islands that utilize different data to establish diverse surrogate models, fostering diverse subpopulations and mitigating the risk of premature convergence. In the intra-island optimization phase, a semi-supervised learning method is devised to fine-tune the surrogates. It not only facilitates …

Full Issue, Volume 20, Issue 4

Journal of Youth Development

No abstract provided.

Developing American Indian/Alaska Native Children As Leaders In The Climate Movement, Joseph Burns, Alessandra Angelino, Danielle Heims-Waldron, Allison Empey, Jason Deen

Journal of Youth Development

American Indian/Alaska Native (AI/AN) voices are critical in the climate movement, as numerous social drivers have rendered these communities particularly vulnerable to the consequences of environmental change. In recent years, specific events, including the Dakota Access Pipeline, have galvanized AI/AN youth, who have been increasingly involved as leaders in the climate movement both in the United States and internationally. This yields a significant opportunity to promote leadership development for Indigenous youth, both through local, national, and international organizing and through curricular development to spark interests in environmental science. This review aims to discuss the role of AI/AN youth leadership in …