Pai Chet Ng

Dr. Pai Chet Ng


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

14 October 2025 in arXiv
Verified
Preprint
Open access
PDF file
DHDion J. X. Ho
Dion J. X. Ho
GRGabriel Lee Jun Rong
Gabriel Lee Jun Rong
NSNiharika Shrivastava
Niharika Shrivastava
HAHarshavardhan Abichandani
Harshavardhan Abichandani
Pai Chet NgPai Chet Ng
Pai Chet Ng
XMXIAOXIAO MIAO
XIAOXIAO MIAO
We present MS-GAGA (Metric-Selective Guided Adversarial Generation Attack), a two-stage framework for crafting transferable and visually imperceptible adversarial examples against deepfake detectors in black-box settings. In Stage 1, a dual-stream attack module generates adversarial candidates: MNTD-PGD applies enhanced gradient calculations optimized for small perturbation budgets, while SG-PGD focuses perturbations on visually salient regions. This complementary design expands the adversarial search space and improves transferability across unseen models. In Stage 2, a metric-aware selection module evaluates candidates based on both their success against black-box models and their structural similarity (SSIM) to the original image. By jointly optimizing transferability and imperceptibility, MS-GAGA achieves up to 27% higher misclassification rates on unseen detectors compared to state-of-the-art attacks.

6 November 2026 in Multimedia Tools and Applications
Verified
Journal Article
Open access
PDF file
HSHaoyu Song
Haoyu Song
Pai Chet NgPai Chet Ng
Pai Chet Ng
Ian McLoughlinIan McLoughlin
Ian McLoughlin
Text-to-image (T2I) generative AI models enable scalable visual content creation but often embed or even amplify societal biases, particularly around gender and object associations. For example, T2I models may reinforce restrictive stereotypes by depicting objects like flowers as feminine or laptops as masculine. Current bias assessment methods often involve multi-step evaluation procedures and typically emphasize aggregate demographic distributions, prompt adherence, or profession-level associations rather than object-level gender–object association analysis. This paper proposes a bias assessment pipeline that combines object detection, perceived-gender identification, object-association scoring, and heatmap visualization to analyse gender–object association bias in T2I-generated images. To support evaluation, we introduce the Object Bias Image Dataset (OBID), designed with a 10,000-image generation target, and evaluate the proposed pipeline on 3,247 retained images that satisfy the requirements for gender–object association analysis. Results reveal stronger class-wise diagonal agreement for neutral objects (0.59) than for male-associated (0.27) and female-associated (0.21) objects, highlighting both the feasibility and current limitations of automated object-association bias assessment.

12 January 2026 in arXiv
Verified
Preprint
Open access
PDF file
OLOlivia Shanhong Liu
Olivia Shanhong Liu
Pai Chet NgPai Chet Ng
Pai Chet Ng
DSDe Wen Soh
De Wen Soh
KPKonstantinos Plataniotis
Konstantinos Plataniotis
Humorous memes blend visual and textual cues to convey irony, satire, or social commentary, posing unique challenges for AI systems that must interpret intent rather than surface correlations. Existing multimodal or prompting-based models generate explanations for humor but operate in an open loop,lacking the ability to critique or refine their reasoning once a prediction is made. We propose FLoReNce, an agentic feedback reasoning framework that treats meme understanding as a closed-loop process during learning and an open-loop process during inference. In the closed loop, a reasoning agent is critiqued by a judge; the error and semantic feedback are converted into control signals and stored in a feedback-informed, non-parametric knowledge base. At inference, the model retrieves similar judged experiences from this KB and uses them to modulate its prompt, enabling better, self-aligned reasoning without finetuning. On the PrideMM dataset, FLoReNce improves both predictive performance and explanation quality over static multimodal baselines, showing that feedback-regulated prompting is a viable path to adaptive meme humor understanding.

28 August 2025 in arXiv
Verified
Preprint
Open access
PDF file
JHJavier Si Zhao Hong
Javier Si Zhao Hong
TDTimothy Zoe Delaya
Timothy Zoe Delaya
SKSherwyn Chan Yin Kit
Sherwyn Chan Yin Kit
Pai Chet NgPai Chet Ng
Pai Chet Ng
XMXIAOXIAO MIAO
XIAOXIAO MIAO
This paper presents our approach to the first Multimodal Personality-Aware Depression Detection Challenge, focusing on multimodal depression detection using machine learning and deep learning models. We explore and compare the performance of XGBoost, transformer-based architectures, and large language models (LLMs) on audio, video, and text features. Our results highlight the strengths and limitations of each type of model in capturing depression-related signals across modalities, offering insights into effective multimodal representation strategies for mental health prediction.