UCD ASEADOS Lab – AI Solution for Cyber Security, Digital Forensics and Smart Systems

Yang and Hong-Hanh have a paper entitled “FreDA: Training-Free Test-Time Adaptation for Deepfake Detection via Non-Parametric Cache Retrieval” accepted for presentation at the 17th EAI International Conference on Digital Forensics & Cyber Crime (ICDF2C-2026), Reykjavik, Iceland, Sept. 2026

Posted on May 13, 2026 by

Well-done Yang and Hong-Hanh! This is Yang's first paper with our ASEADOS group. Abstract: Deepfake (DF) detectors face significant challenges when deployed in real-world environments, particularly when encountering test samples deviated from training data through either distribution shifts or post-processing manipulations. To address these challenges, we propose FreDA (Free Detection...

Hong-Hanh got EuroHPC AI Factory for Science Award!

Posted on May 1, 2026 by

Congratulations to Hong-Hanh! Her research proposal has been awarded compute resources through the EuroHPC AI Factory for Science and Collaborative EU Projects programme! The award provides 60,000 node hours on MeluXina GPU (~€300K in commercial cloud equivalent). Proposals are evaluated through rigorous technical and expert peer-review, assessed on excellence, innovation and impact, and...

Congratulations to Hong and Dat-Thinh, who have just passed the Stage Transfer Assessment!

Posted on April 7, 2026 by

Well-done, Hong and Dat-Thinh! and welcome to the PhD Stage 2! You're now official PhD candidates. We also take this opportunity to thank the STA assessment panel members who gave positive feedback and constructive comments to Hong and Dat-Thinh.

Tharindu has a paper, “ASEADOS-SDN-IoT: A Novel SDN-IoT Network Intrusion Detection Dataset and Framework”, has been published in the Elsevier Internet of Things journal (IF: 7.6, Q1), March 2026

Posted on March 12, 2026 by

Excited to share our latest research paper — “ASEADOS-SDN-IoT: A Novel SDN-IoT Network Intrusion Detection Dataset and Framework” — has been accepted for publication in the Internet of Things journal (Elsevier – Q1, IF - 7.6). This work introduces a publicly available SDN-IoT intrusion detection dataset generated from a hybrid testbed integrating physical IoT devices with SDN...

Duc-Anh Secured EU ENFIELD Funding on Multimodal Activity Log and Feature Summarisation

Posted on March 8, 2026 by

We are delighted to announce that Duc-Anh has been awarded a competitive grant from the ENFIELD project, 4th call (funded by Horizon Europe) for the project entitled “Work shift reporting with multimodal activity log and feature summarization” . Well-done, Duc-Anh! EU ENFIELD Funding: European Lighthouse to Manifest Trustworthy and Green AI (ENFIELD), an EU funding...

Hong-Hanh Represented at AAAI-26 in Singapore

Posted on January 24, 2026 by

Hong-Hanh is currently on the ground at the 40th Annual AAAI Conference on Artificial Intelligence (AAAI-26) at the Singapore EXPO!This week (Jan 20–27), Hong-Hanh is representing the lab, sharing our research on "Beyond Binary Classification: A Semi-supervised Approach to Generalized AI-generated Image Detection" and connecting with the international AI community.

Quang-Tien has a paper, “Concept drift detection in image data stream: a survey on current literature, limitations and future directions”, has been published in the Springer Artificial Intelligence Review (IF: 14.9, Q1), December 2025

Posted on January 19, 2026 by

We are thrilled to announce that our lab’s latest paper, Concept drift detection in image data stream: a survey on current literature, limitations and future directions”, has been published in the Springer Artificial Intelligence Review (IF: 14.9, Q1). Congratulate Quang-Tien! Well-done! This paper presents the first comprehensive review of concept drift detection methods tailored for image...

Hong-Hanh Secured ENFIELD Funding to Combat Advanced Audio Deepfakes

Posted on March 8, 2026 by

We are delighted to announce that Hong-Hanh has been awarded a competitive grant from the ENFIELD project (funded by Horizon Europe) to advance the state-of-the-art in voice security. The proposal, titled "Generalization of Deepfake Voice Detection across Generator Architectures," has secured €24,000 in funding to address critical challenges in biometric security. Project Overview. As...

Tharindu has a paper, “Evaluating the Robustness of DL-Based AAD in SDN-IoT Networks Against OOD Data and Poisoning Attacks Using Autoencoders”, has been published in the Springer Journal of Network and Systems Management (IF: 3.9, Q1), Dec 2025

Posted on December 2, 2025 by

We are thrilled to announce that our lab’s latest paper, “Evaluating the Robustness of DL-Based AAD in SDN-IoT Networks Against OOD Data and Poisoning Attacks Using Autoencoders,” has been accepted for publication in the Springer Journal of Network and Systems Management (Special Issue: Cyber-Security in Software-defined and Virtualized Infrastructures). Congratulate Tharindu! This work...

Hong-Hanh has a paper, “A Survey on Proactive Deepfake Defense: Disruption and Watermarking”, accepted to publication on ACM Computing Surveys

Posted on November 10, 2025 by

We are thrilled to announce that our lab's latest paper, "A Survey on Proactive Deepfake Defense: Disruption and Watermarking," has been accepted for publication in the prestigious journal ACM Computing Surveys (CSUR). Our Focus: Proactive Defense Our survey provides a comprehensive review of proactive defense mechanisms. These strategies are designed to prevent the generation of malicious...