Wen-Chao Yang

Prof. Wen-Chao Yang

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
19 October 2020 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
WYWen-Chao Yang
Wen-Chao Yang
JJJiajun Jiang
Jiajun Jiang
CCChung-Hao Chen
Chung-Hao Chen

17 October 2023 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
WYWen-Chao Yang
Wen-Chao Yang
JJJiajun Jiang
Jiajun Jiang
AMAustin Mao
Austin Mao
KSKai-An Su
Kai-An Su
CCChung-Hao Chen
Chung-Hao Chen

17 November 2025 in Electronics
Verified
Journal Article
Open access
PDF file
NHNhi Huynh
Nhi Huynh
JJJIAJUN JIANG
JIAJUN JIANG
CCChung-Hao Chen
Chung-Hao Chen
WYWen-Chao Yang
Wen-Chao Yang
With the increasing sophistication of Artificial Intelligence (AI), traditional digital steganography methods face a growing risk of being detected and compromised. Adversarial attacks, in particular, pose a significant threat to the security and robustness of hidden information. To address these challenges, this paper proposes a novel AI-based steganography framework designed to enhance the security of concealed messages within digital images. Our approach introduces a multi-stage embedding process that utilizes a sequence of encoder models, including a base encoder, a residual encoder, and a dense encoder, to create a more complex and secure hiding environment. To further improve robustness, we integrate Wavelet Transforms with various deep learning architectures, namely Convolutional Neural Networks (CNNs), Bayesian Neural Networks (BNNs), and Graph Convolutional Networks (GCNs). We conducted a comprehensive set of experiments on the FashionMNIST and MNIST datasets to evaluate our framework’s performance against several adversarial attacks. The results demonstrate that our multi-stage approach significantly enhances resilience. Notably, while CNN architectures provide the highest baseline accuracy, BNNs exhibit superior intrinsic robustness against gradient-based attacks. For instance, under the Fast Gradient Sign Method (FGSM) attack on the MNIST dataset, our BNN-based models maintained an accuracy of over 98%, whereas the performance of comparable CNN models dropped sharply to between 10% and 18%. This research provides a robust and effective method for developing next-generation secure steganography systems.

17 August 2025 in Electronics
Verified
Journal Article
Open access
PDF file
WYWen-Chao Yang
Wen-Chao Yang
CSChih-Hung Shih
Chih-Hung Shih
JJJIAJUN JIANG
JIAJUN JIANG
SESergio Pallas Enguita
Sergio Pallas Enguita
CCChung-Hao Chen
Chung-Hao Chen
Understanding human perceptual strategies in high-stakes environments, such as crime scene investigations, is essential for developing cognitive models that reflect expert decision-making. This study presents an immersive experimental framework that utilizes virtual reality (VR) and eye-tracking technologies to capture and analyze visual attention during simulated forensic tasks. A360° panoramic crime scene, constructed using the Nikon KeyMission 360 camera, was integrated into a VR system with HTC Vive and Tobii Pro eye-tracking components. A total of 46 undergraduate students aged 19 to 24–23, from the National University of Singapore in Singapore and 23 from the Central Police University in Taiwan—participated in the study, generating over 2.6 million gaze samples (IRB No. 23-095-B). The collected eye-tracking data were analyzed using statistical summarization, temporal alignment techniques (Earth Mover’s Distance and Needleman-Wunsch algorithms), and machine learning models, including K-means clustering, random forest regression, and support vector machines (SVMs). Clustering achieved a classification accuracy of 78.26%, revealing distinct visual behavior patterns across participant groups. Proficiency prediction models reached optimal performance with a random forest regression (R2 = 0.7034), highlighting scan-path variability and fixation regularity as key predictive features. These findings demonstrate that eye-tracking metrics—particularly sequence-alignment-based features—can effectively capture differences linked to both experiential training and cultural context. Beyond its immediate forensic relevance, the study contributes a structured methodology for encoding visual attention strategies into analyzable formats, offering valuable insights for cognitive modeling, training systems, and human-centered design in future perceptual intelligence applications. Furthermore, our work advances the development of autonomous vehicles by modeling how humans visually interpret complex and potentially hazardous environments. By examining expert and novice gaze patterns during simulated forensic investigations, we provide insights that can inform the design of autonomous systems required to make rapid, safety-critical decisions in similarly unstructured settings. The extraction of human-like visual attention strategies not only enhances scene understanding, anomaly detection, and risk assessment in autonomous driving scenarios, but also supports accelerated learning of response patterns for rare, dangerous, or otherwise exceptional conditions—enabling autonomous driving systems to better anticipate and manage unexpected real-world challenges.

13 January 2026 in Sensors
Verified
Journal Article
Open access
PDF file
HLHsiang-Ju Lai
Hsiang-Ju Lai
LTLong-Huang Tsai
Long-Huang Tsai
HKHSU KUNGYANG
HSU KUNGYANG
WYWen-Chao Yang
Wen-Chao Yang
With the rapid advancement of technology in recent years, signatures on contracts and documents have increasingly shifted from traditional handwritten forms on paper to digital handwritten signatures executed on devices (hereafter referred to as digital tablets). This transition introduces new challenges for forensic document examination due to the differences in writing instruments. According to the European Network of Forensic Science Institutes (ENFSI), a Digital Capture Signature (DCS) refers to data points captured during the writing process on digital devices such as tablets, smartphones, or signature pads. In addition to retaining the visual image of the signature, DCS provides more information previously unavailable, including pen pressure, stroke order, and writing speed. These features possess potential forensic value and warrant further study and evaluation. This study employs three devices—Samsung Galaxy Tab S10, Apple iPad Pro, and Apple iPad Mini—together with their respective styluses as experimental tools. Using custom-developed handwriting capture software for both Android and iOS platforms, we simulated signature-writing scenarios common in the financial and insurance industries. Thirty participants were asked to provide samples of horizontal Chinese, English, and number writings (FUJ-IRB NO: C113187), which were subsequently normalized and segmented into characters. For analysis, we adopted distance-based time-series alignment algorithms (FastDTW and SC-DTW) to match writing data across different instances (intra- and inter-writer). The accumulated distances between corresponding data points, such as coordinates and pressure, were used to assess handwriting stability and to study the differences between same-writer and different-writer samples. The findings indicate that preprocessing through character centroid alignment, followed by the analysis, substantially reduces the average accumulated distance of handwriting. This procedure quantifies the stability of an individual’s handwriting and enables differentiation between same-writer and different-writer scenarios based on the distribution of DCS distances. Furthermore, the use of styluses provides more precise distinctions between same- and different-writer samples compared with direct finger-based writing. In the context of rapid advancements in artificial intelligence and emerging technologies, this preliminary study aims to contribute foundational insights into the forensic application of digital signature examination.

11 October 2025 in Eng
Verified
Journal Article
Open access
PDF file
JJJIAJUN JIANG
JIAJUN JIANG
WYWen-Chao Yang
Wen-Chao Yang
CCChung-Hao Chen
Chung-Hao Chen
TYTimothy Young
Timothy Young
Deepfake technology, which utilizes advanced AI models such as Generative Adversarial Networks (GANs), has led to the proliferation of highly convincing manipulated media, posing significant challenges for detection. Existing detection methods often struggle with the low-quality or compressed press, which is prevalent on social media platforms. This paper proposes a novel Deepfake detection framework that leverages No-Reference Image Quality Assessment (NRIQA) techniques, specifically, BRISQUE, NIQE, and PIQUE, to extract quality-related features from facial images. These features are then classified using a Support Vector Machine (SVM) with various kernel functions. We evaluate our method under both intra-dataset and cross-dataset settings. For intra-dataset evaluation, we conduct K-fold cross-validation on two benchmark datasets, DFDC and Celeb-DF (v2), including downsampled versions to simulate real-world degradation. The results show that our method maintains high accuracy even under significant quality loss, achieving up to 98% accuracy on the Celeb-DF (v2) dataset and outperforming several state-of-the-art methods. To improve the transferability of the detection models, we introduce an integrated filtering strategy based on NR-IQA thresholding, which enhances performance in cross-dataset transfer scenarios. This approach yields up to 7% improvement in detection accuracy under challenging cross-domain conditions.