29 citations · 56 across the 18 of their papers we have counts for
18 papers
Estimating Exam Item Difficulty with LLMs: A Benchmark on Brazil's ENEM Corpus
Thiago Brant, Julien Kühn, Jun Pang
As Large Language Models (LLMs) are increasingly deployed to generate educational content, a critical safety question arises: can these models reliably estimate the difficulty of t…
Malicious Repurposing of Open Science Artefacts by Using Large Language Models
Zahra Hashemi, Zhiqiang Zhong, Jun Pang +1
The rapid evolution of large language models (LLMs) has fuelled enthusiasm about their role in advancing scientific discovery, with studies exploring LLMs that autonomously generat…
NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning
Jiayu Xu, Junbiao Pang
Learning from Noisy Labels (LNL) remains a fundamental challenge in deep learning because real-world datasets often contain corrupted annotations. Most existing methods rely on lab…
Evaluating Multi-Agent Defences Against Jailbreaking Attacks on Large Language Models
Maria Carolina Cornelia Wit, Jun Pang
Recent advances in large language models (LLMs) have raised concerns about jailbreaking attacks, i.e., prompts that bypass safety mechanisms. This paper investigates the use of mul…
Ownership Protection of Generative Adversarial Networks
Hailong Hu, Jun Pang
Generative adversarial networks (GANs) have shown remarkable success in image synthesis, making GAN models themselves commercially valuable to legitimate model owners. Therefore, i…
PriSampler: Mitigating Property Inference of Diffusion Models
Hailong Hu, Jun Pang
Diffusion models have been remarkably successful in data synthesis. However, when these models are applied to sensitive datasets, such as banking and human face data, they might br…
Membership Inference of Diffusion Models
Hailong Hu, Jun Pang
Recent years have witnessed the tremendous success of diffusion models in data synthesis. However, when diffusion models are applied to sensitive data, they also give rise to sever…
"Double vaccinated, 5G boosted!": Learning Attitudes towards COVID-19 Vaccination from Social Media
Ninghan Chen, Xihui Chen, Zhiqiang Zhong +1
To address the vaccine hesitancy which impairs the efforts of the COVID-19 vaccination campaign, it is imperative to understand public vaccination attitudes and timely grasp their…
Simplifying Node Classification on Heterophilous Graphs with Compatible Label Propagation
Zhiqiang Zhong, Sergey Ivanov, Jun Pang
Graph Neural Networks (GNNs) have been predominant for graph learning tasks; however, recent studies showed that a well-known graph algorithm, Label Propagation (LP), combined with…
Unsupervised Network Embedding Beyond Homophily
Zhiqiang Zhong, Guadalupe Gonzalez, Daniele Grattarola +1
Network embedding (NE) approaches have emerged as a predominant technique to represent complex networks and have benefited numerous tasks. However, most NE approaches rely on a hom…
The Burden of Being a Bridge: Analysing Subjective Well-Being of Twitter Users during the COVID-19 Pandemic
Ninghan Chen, Xihui Chen, Zhiqiang Zhong +1
The outbreak of the COVID-19 pandemic triggers infodemic over online social media, which significantly impacts public health around the world, both physically and psychologically.…
Model Extraction and Defenses on Generative Adversarial Networks
Hailong Hu, Jun Pang
Model extraction attacks aim to duplicate a machine learning model through query access to a target model. Early studies mainly focus on discriminative models. Despite the success,…
From #Jobsearch to #Mask: Improving COVID-19 Cascade Prediction with Spillover Effects
Ninghan Chen, Xihui Chen, Zhiqiang Zhong +1
An information outbreak occurs on social media along with the COVID-19 pandemic and leads to infodemic. Predicting the popularity of online content, known as cascade prediction, al…
Semantic and Relational Spaces in Science of Science: Deep Learning Models for Article Vectorisation
Diego Kozlowski, Jennifer Dusdal, Jun Pang +1
Over the last century, we observe a steady and exponentially growth of scientific publications globally. The overwhelming amount of available literature makes a holistic analysis o…
Personalised Meta-path Generation for Heterogeneous GNNs
Zhiqiang Zhong, Cheng-Te Li, Jun Pang
Recently, increasing attention has been paid to heterogeneous graph representation learning (HGRL), which aims to embed rich structural and semantic information in heterogeneous in…
Multi-grained Semantics-aware Graph Neural Networks
Zhiqiang Zhong, Cheng-Te Li, Jun Pang
Graph Neural Networks (GNNs) are powerful techniques in representation learning for graphs and have been increasingly deployed in a multitude of different applications that involve…
Hierarchical Message-Passing Graph Neural Networks
Zhiqiang Zhong, Cheng-Te Li, Jun Pang
Graph Neural Networks (GNNs) have become a prominent approach to machine learning with graphs and have been increasingly applied in a multitude of domains. Nevertheless, since most…
An Exploratory Study of COVID-19 Information on Twitter in the Greater Region
Ninghan Chen, Zhiqiang Zhong, Jun Pang
The outbreak of the COVID-19 leads to a burst of information in major online social networks (OSNs). Facing this constantly changing situation, OSNs have become an essential platfo…