Publications

Research from GMD-AI. · 15

* Corresponding author·† Co-first author

YearTypeAuthor

2026(6)

UB-SMoE: Universally Balanced Sparse Mixture-of-Experts for Resource-adaptive Federated Fine-tuning of Foundation Models

Van-Tuan Tran, Hong-Hanh Nguyen-Le, Marco Ruffini, Merim Dzaferagic

Proceedings of the International Conference on Machine Learning (ICML)2026conference

mixture of expertsfederated fine-tuningresource-adaptivefoundation modelsLoRA

PDF arXiv

AFSS: Artifact-Focused Self-Synthesis for Mitigating Bias in Audio Deepfake Detection

Hai-Son Nguyen-Le, Hung-Cuong Nguyen-Thanh, Nhien-An Le-Khac, Thuc D. Nguyen, Hong-Hanh Nguyen-Le^*

International Joint Conference on Neural Networks (IJCNN)2026conference

audio deepfake detectionbias mitigationself-synthesisgeneralization

arXiv Code

Beyond Binary Classification: A Semi-supervised Approach to Generalized AI-generated Image Detection

Hong-Hanh Nguyen-Le, Van-Tuan Tran, Thuc D. Nguyen, Nhien-An Le-Khac

Proceedings of the AAAI Conference on Artificial Intelligence2026conference

passive deepfake detectiongeneralizationcross-generator detectiondeep clustering

PDF arXiv Code

Transferable Multi-Bit Watermarking Across Frozen Diffusion Models via Latent Consistency Bridges

Hong-Hanh Nguyen-Le^†, Van-Tuan Tran^†, Thuc D. Nguyen, Nhien-An Le-Khac

Second Workshop on Technical AI Governance Research (TAIGR 2026)2026workshop

watermarkingdiffusion modelscontent provenanceAI governancelatent consistency models

arXiv

How Effective Are Publicly Accessible Deepfake Detection Tools? A Comparative Evaluation of Open-Source and Free-to-Use Platforms

Michael Rettinger, Ben Beaumont, Nhien-An Le-Khac, Hong-Hanh Nguyen-Le^*

Preprint (arXiv)2026preprint

deepfake detectiondigital forensicdigital media authenticityempirical evaluationsurvey

arXiv Code

Deepfake Detection Across Image, Video, and Audio: A Comprehensive Survey with Empirical Evaluation of Generalization and Robustness

Hong-Hanh Nguyen-Le, Van-Tuan Tran, Thuc D. Nguyen, Nhien-An Le-Khac

Springer AI Review2026journal

passive deepfake detectiongeneralizationrobustnessempirical evaluationcross-modality analysissurvey

PDF

2025(6)

Blockchain-based vs. SQL Database Systems for Digital Twin Evidence Management: A Comparative Forensic Analysis

Boyd Franken, Hong-Hanh Nguyen-Le, Nhien-An Le-Khac

EAI International Conference on Digital Forensics & Cyber Crime 20252025conference

digital twinsblockchainSQL databaseevidence management

PDF

A survey on proactive deepfake defense: Disruption and watermarking

Hong-Hanh Nguyen-Le, Van-Tuan Tran, Thuc D. Nguyen, Nhien-An Le-Khac

ACM Computing Surveys2025journal

proactive deepfake detection disruptionwatermarkinggenerative AIsurvey

PDF

Revisiting Sparse Mixture of Experts for Resource-adaptive Federated Fine-tuning Foundation Models

Van-Tuan Tran, Khiem Le, Quoc-Viet Pham

ICLR 2025 Workshop on Modularity for Collaborative, Decentralized, and Continual Deep Learning2025workshop

Resource-adaptivemixture of expertsfederated fine-tuningfoundation models

PDF Code

ToFU: Transforming How Federated Learning Systems Forget User Data

Van-Tuan Tran, Hong-Hanh Nguyen-Le, Quoc-Viet Pham

28th European Conference on Artificial Intelligence (ECAI-25)2025conference

federated unlearninglearning-to-unlearn

PDF arXiv Code

Think Twice Before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation

Hong-Hanh Nguyen-Le, Van-Tuan Tran, Thuc D. Nguyen, Nhien-An Le-Khac

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence2025conference

passive deepfake detectiontest time adaptationnegative learning

PDF arXiv Code

Privacy-preserving speaker verification system using Ranking-of-Element hashing

Hong-Hanh Nguyen-Le, Lam Tran, Dinh Song An Nguyen, Nhien-An Le-Khac, Thuc D. Nguyen

Pattern Recognition2025journal

template protectionwinner-takes-all hasingbiometric verificationprivacy-preserving machine learning

PDF

2024(3)

Improving Security in Internet of Medical Things through Hierarchical Cyberattacks Classification

Vince Noort, Nhien-An Le-Khac, Hong-Hanh Nguyen-Le^*

IEEE 23rd International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)2024conference

internet of medical thingscybersecurityhierarchical classificationclass of cyberattacks

PDF

Personalized Privacy-Preserving Framework for Cross-Silo Federated Learning

Van-Tuan Tran, Huy-Hieu Pham, Kok-Seng Wong

IEEE Transactions on Emerging Topics in Computing2024journal

cross-Silo federated learningdifferential privacygenerative adversarial networkspersonalized federated learning

PDF Code

D-CAPTCHA++: A Study of Resilience of Deepfake CAPTCHA under Transferable Imperceptible Adversarial Attack

Hong-Hanh Nguyen-Le, Van-Tuan Tran, Thuc D. Nguyen, Nhien-An Le-Khac

International Joint Conference on Neural Networks (IJCNN)2024conference

black-box attackstransferabilityimperceptible adversarial examplesdeepfake CAPTCHA

PDF arXiv Code

Publications

Biometric Verification(1)

Privacy-preserving speaker verification system using Ranking-of-Element hashing

Cybersecurity/Digital Forensics(2)

Blockchain-based vs. SQL Database Systems for Digital Twin Evidence Management: A Comparative Forensic Analysis

Improving Security in Internet of Medical Things through Hierarchical Cyberattacks Classification

Deepfake Detection(8)

AFSS: Artifact-Focused Self-Synthesis for Mitigating Bias in Audio Deepfake Detection

Beyond Binary Classification: A Semi-supervised Approach to Generalized AI-generated Image Detection

Transferable Multi-Bit Watermarking Across Frozen Diffusion Models via Latent Consistency Bridges

How Effective Are Publicly Accessible Deepfake Detection Tools? A Comparative Evaluation of Open-Source and Free-to-Use Platforms

Deepfake Detection Across Image, Video, and Audio: A Comprehensive Survey with Empirical Evaluation of Generalization and Robustness

A survey on proactive deepfake defense: Disruption and watermarking

Think Twice Before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation

D-CAPTCHA++: A Study of Resilience of Deepfake CAPTCHA under Transferable Imperceptible Adversarial Attack

Federated Learning(4)

UB-SMoE: Universally Balanced Sparse Mixture-of-Experts for Resource-adaptive Federated Fine-tuning of Foundation Models

Revisiting Sparse Mixture of Experts for Resource-adaptive Federated Fine-tuning Foundation Models

ToFU: Transforming How Federated Learning Systems Forget User Data

Personalized Privacy-Preserving Framework for Cross-Silo Federated Learning

Unlearning(1)

ToFU: Transforming How Federated Learning Systems Forget User Data

2026(6)

UB-SMoE: Universally Balanced Sparse Mixture-of-Experts for Resource-adaptive Federated Fine-tuning of Foundation Models

AFSS: Artifact-Focused Self-Synthesis for Mitigating Bias in Audio Deepfake Detection

Beyond Binary Classification: A Semi-supervised Approach to Generalized AI-generated Image Detection

Transferable Multi-Bit Watermarking Across Frozen Diffusion Models via Latent Consistency Bridges

How Effective Are Publicly Accessible Deepfake Detection Tools? A Comparative Evaluation of Open-Source and Free-to-Use Platforms

Deepfake Detection Across Image, Video, and Audio: A Comprehensive Survey with Empirical Evaluation of Generalization and Robustness

2025(6)

Blockchain-based vs. SQL Database Systems for Digital Twin Evidence Management: A Comparative Forensic Analysis

A survey on proactive deepfake defense: Disruption and watermarking

Revisiting Sparse Mixture of Experts for Resource-adaptive Federated Fine-tuning Foundation Models

ToFU: Transforming How Federated Learning Systems Forget User Data

Think Twice Before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation

Privacy-preserving speaker verification system using Ranking-of-Element hashing

2024(3)

Improving Security in Internet of Medical Things through Hierarchical Cyberattacks Classification

Personalized Privacy-Preserving Framework for Cross-Silo Federated Learning

D-CAPTCHA++: A Study of Resilience of Deepfake CAPTCHA under Transferable Imperceptible Adversarial Attack