Publications
2026
- PreprintTransferable Multi-Bit Watermarking Across Frozen Diffusion Models via Latent Consistency BridgesHong-Hanh Nguyen-Le, Van-Tuan Tran, Dinh-Thuc Nguyen, and Nhien-An Le-KhacarXiv preprint arXiv:2506.16600, 2026
As diffusion models (DMs) enable photorealistic image generation at unprecedented scale, watermarking techniques have become essential for provenance establishment and accountability. Existing methods face challenges: sampling-based approaches operate on frozen models but require costly N-step Denoising Diffusion Implicit Models (DDIM) inversion (typically N=50) for zero-bit-only detection; fine-tuning-based methods achieve fast multi-bit extraction but couple the watermark to a specific model checkpoint, requiring retraining for each architecture. We propose DiffMark, a plug-and-play watermarking method that offers three key advantages over existing approaches: single-pass multi-bit detection, per-image key flexibility, and cross-model transferability. Rather than encoding the watermark into the initial noise vector, DiffMark injects a persistent learned perturbation δat every denoising step of a completely frozen DM. The watermark signal accumulates in the final denoised latent z_0 and is recovered in a single forward pass. The central challenge of backpropagating gradients through a frozen UNet without traversing the full denoising chain is addressed by employing Latent Consistency Models (LCM) as a differentiable training bridge. This reduces the number of gradient steps from 50 DDIM to 4 LCM and enables a single-pass detection at 16.4 ms, a 45\times speedup over sampling-based methods. Moreover, by this design, the encoder learns to map any runtime secret to a unique perturbation at inference time, providing genuine per-image key flexibility and transferability to unseen diffusion-based architectures without per-model fine-tuning. Although achieving these advantages, DiffMark also maintains competitive watermark robustness against distortion, regeneration, and adversarial attacks.
- AAAIBeyond Binary Classification: A Semi-supervised Approach to Generalized AI-generated Image DetectionHong-Hanh Nguyen-Le, Van-Tuan Tran, and Nhien-An Le-KhacIn Proceedings of the AAAI Conference on Artificial Intelligence, 2026
Deepfake (DF) detectors face significant challenges when deployed in real-world environments, particularly when encountering test samples deviated from training data through either postprocessing manipulations or distribution shifts. We demonstrate postprocessing techniques can completely obscure generation artifacts presented in DF samples, leading to performance degradation of DF detectors. To address these challenges, we propose Think Twice before Adaptation (T2A), a novel online test-time adaptation method that enhances the adaptability of detectors during inference without requiring access to source training data or labels. Our key idea is to enable the model to explore alternative options through an Uncertainty-aware Negative Learning objective rather than solely relying on its initial predictions as commonly seen in entropy minimization (EM)-based approaches. We also introduce an Uncertain Sample Prioritization strategy and Gradients Masking technique to improve the adaptation by focusing on important samples and model parameters. Our theoretical analysis demonstrates that the proposed negative learning objective exhibits complementary behavior to EM, facilitating better adaptation capability. Empirically, our method achieves state-of-the-art results compared to existing test-time adaptation (TTA) approaches and significantly enhances the resilience and generalization of DF detectors during inference.
- arXivHow Effective Are Publicly Accessible Deepfake Detection Tools? A Comparative Evaluation of Open-Source and Free-to-Use PlatformsMichael Rettinger, Benjamin Beaumont, Nhien-An Le-Khac, and Hong-Hanh Nguyen-LearXiv preprint arXiv:2603.04456, 2026
The proliferation of deepfake imagery poses escalating challenges for practitioners tasked with verifying digital media authenticity. While detection algorithm research is abundant, empirical evaluations of publicly accessible tools that practitioners actually use remain scarce. This paper presents the first cross-paradigm evaluation of six tools, spanning two complementary detection approaches: forensic analysis tools (InVID & WeVerify, FotoForensics, Forensically) and AI-based classifiers (DecopyAI, FaceOnLive, Bitmind). Both tool categories were evaluated by professional investigators with law enforcement experience using blinded protocols across datasets comprising authentic, tampered, and AI-generated images sourced from DF40, CelebDF, and CASIA-v2. We report three principal findings: forensic tools exhibit high recall but poor specificity, while AI classifiers demonstrate the inverse pattern; human evaluators substantially outperform all automated tools; and human-AI disagreement is asymmetric, with human judgment prevailing in the vast majority of discordant cases. We discuss implications for practitioner workflows and identify critical gaps in current detection capabilities.
2025
- Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time AdaptationHong-Hanh Nguyen-Le, Van-Tuan Tran, Dinh-Thuc Nguyen, and Nhien-An Le-Khac34th International Joint Conference on Artificial Intelligence, 2025
Deepfake (DF) detectors face significant challenges when deployed in real-world environments, particularly when encountering test samples deviated from training data through either postprocessingmanipulations or distribution shifts. We demonstrate postprocessing techniques can completely obscure generation artifacts presented in DF samples, leading to performance degradation of DF detectors. To address these challenges, we propose Think Twice before Adaptation (T2A), a novel online test-time adaptation method that enhances the adaptability of detectors during inference without requiring access to source training data or labels. Our key idea is to enable the model to explore alternative options through an Uncertainty-aware Negative Learning objective rather than solely relying on its initial predictions as commonly seen in entropy minimization (EM)-based approaches. We also introduce an Uncertain Sample Prioritization strategy and Gradients Masking technique to improve the adaptation by focusing on important samples and model parameters. Our theoretical analysis demonstrates that the proposed negative learning objective exhibits complementary behavior to EM, facilitating better adaptation capability. Empirically, our method achieves state-of-the-art results compared to existing test-time adaptation (TTA) approaches and significantly enhances the resilience and generalization of DF detectors during inference.
- Privacy-preserving speaker verification system using Ranking-of-Element hashingHong-Hanh Nguyen-Le, Lam Tran, Dinh Song An Nguyen, Nhien-An Le-Khac, and Thuc NguyenPattern Recognition, 2025
The advancements in automatic speaker recognition have led to the exploration of voice data for verification systems. This raises concerns about the security of storing voice templates in plaintext. In this paper, we propose a novel cancellable biometrics that does not require users to manage random matrices or tokens. First, we pre-process the raw voice data and feed it into a deep feature extraction module to obtain embeddings. Next, we propose a hashing scheme, Ranking-of-Elements, which generates compact hashed codes by recording the number of elements whose values are lower than that of a random element. This approach captures more information from smaller-valued elements and prevents the adversary from guessing the ranking value through Attacks via Record Multiplicity. Lastly, we introduce a fuzzy matching method, to mitigate the variations in templates resulting from environmental noise. We evaluate the performance and security of our method on two datasets: TIMIT and VoxCeleb1.
- ACM CSURA Survey on Proactive Deepfake Defense: Disruption and WatermarkingHong-Hanh Nguyen-Le, Van-Tuan Tran, Dinh-Thuc Nguyen, and Nhien-An Le-KhacACM Computing Surveys, 2025
The rapid proliferation of generative AI has led to led to unprecedented capabilities in synthesizing realistic deepfakes (DFs) across multiple modalities. This raises significant concerns regarding privacy, security, and copyright protection. Unlike passive detection approaches that operate after DFs have been created and distributed, proactive defense mechanisms aim at preventing the generation of malicious synthetic content at its source. This article provides a comprehensive survey of current proactive DF defense strategies, including Disruption and Watermarking. Disruption approaches protect individuals data by introducing imperceptible perturbations that prevent unauthorized exploitation by generative models, while watermarking approaches embed verifiable messages into data or models to enable content authentication and attribution. We also analyze proactive approaches across various evaluation metrics (imperceptibility, protectability/detectability, transferability, traceability, and robustness), and examine their effectiveness in real-world settings. Furthermore, we review the evolution of DF generation techniques, highlighting their rapid developments. Finally, we identify key challenges and promising future research directions to enhance proactive defense mechanisms.
- PreprintDeepfake Detection Across Image, Video, and Audio: A Comprehensive Survey with Empirical Evaluation of Generalization and RobustnessHong-Hanh Nguyen-Le, Van-Tuan Tran, Dinh-Thuc Nguyen, and Nhien-An Le-Khac2025
- ToFU: Transforming How Federated Learning Systems Forget User DataTran Van-Tuan, Hong-Hanh Nguyen-Le, and Quoc-Viet Pham2025
Neural networks unintentionally memorize training data, creating privacy risks in federated learning (FL) systems, such as inference and reconstruction attacks on sensitive data. To mitigate these risks and to comply with privacy regulations, Federated Unlearning (FU) has been introduced to enable participants in FL systems to remove their data’s influence from the global model. However, current FU methods primarily act post-hoc, struggling to efficiently erase information deeply memorized by neural networks. We argue that effective unlearning necessitates a paradigm shift: designing FL systems inherently amenable to forgetting. To this end, we propose a learning-to-unlearn Transformation-guided Federated Unlearning (ToFU) framework that incorporates transformations during the learning process to reduce memorization of specific instances. Our theoretical analysis reveals how transformation composition provably bounds instance-specific information, directly simplifying subsequent unlearning. Crucially, ToFU can work as a plug-and-play framework that improves the performance of existing FU methods. Experiments on CIFAR-10, CIFAR-100, and the MUFAC benchmark show that ToFU outperforms existing FU baselines, enhances performance when integrated with current methods, and reduces unlearning time.
- ICDF2CBlockchain-based vs. SQL Database Systems for Digital Twin Evidence Management: A Comparative Forensic AnalysisFrancis Boyd, Hong-Hanh Nguyen-Le, and Nhien-An Le-KhacIn 16th EAI International Conference on Digital Forensics & Cyber Crime (ICDF2C), 2025
Digital forensics faces unprecedented challenges with the emergence of digital twins and metaverse technologies. This paper presents the first comparative analysis between blockchain-based and traditional database systems for managing digital twin evidence in forensic investigations. We conducted controlled experiments comparing the Ethereum blockchain with IPFS storage against traditional SQL databases for digital twin evidence management. Our findings reveal that while blockchain provides superior data integrity and immutability, crucial for forensic applications, traditional databases offer better performance consistency. The blockchain implementation showed faster average storage times but higher variability in retrieval operations. Both systems maintained forensic integrity through hash verification, though blockchain immutable nature provides additional security guarantees essential for legal proceedings. This research contributes to the development of robust digital forensic methodologies for emerging technologies in the metaverse era.
2024
- Improving Security in Internet of Medical Things through Hierarchical Cyberattacks ClassificationVince Noort, Nhien-An Le-Khac, and Hong-Hanh Nguyen-LeIn 2024 IEEE 23rd International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom), 2024
- D-CAPTCHA++: A Study of Resilience of Deepfake CAPTCHA under Transferable Imperceptible Adversarial AttackHong-Hanh Nguyen-Le, Van-Tuan Tran, Dinh-Thuc Nguyen, and Nhien-An Le-KhacIn 2024 International Joint Conference on Neural Networks (IJCNN), 2024
The advancements in generative AI have enabled the improvement of audio synthesis models, including text-to-speech and voice conversion. This raises concerns about its potential misuse in social manipulation and political interference, as synthetic speech has become indistinguishable from natural human speech. Several speech-generation programs are utilized for malicious purposes, especially impersonating individuals through phone calls. Therefore, detecting fake audio is crucial to maintain social security and safeguard the integrity of information. Recent research has proposed a D-CAPTCHA system based on the challenge-response protocol to differentiate fake phone calls from real ones. In this work, we study the resilience of this system and introduce a more robust version, D-CAPTCHA++, to defend against fake calls. Specifically, we first expose the vulnerability of the D-CAPTCHA system under the transferable imperceptible adversarial attack. Secondly, we mitigate such vulnerability by improving the robustness of the system by using adversarial training in D-CAPTCHA deepfake detectors and task classifiers.
- PreprintDeepfake Generation and Proactive Deepfake Defense: A Comprehensive SurveyHong-Hanh Nguyen-Le, Van-Tuan Tran, Dinh-Thuc Nguyen, and Nhien-An Le-KhacAuthorea Preprints, 2024
The proliferation of highly realistic deepfakes, powered by Generative Artificial Intelligence (GenAI), presents significant challenges to digital trust and security. This survey provides a comprehensive overview of proactive deepfake detection approaches, including disruption and watermarking methods. Our survey provides a taxonomy of these strategies based on their existing methodologies and extend the discussion to other perspectives, including imperceptibility, transferability, universality, and robustness. We also explore the associated threat models, considering various adversary objectives and capabilities. Additionally, we review state-of-the-art deepfake generation techniques that provide context for the challenges faced by detection methods.
- PreprintPassive Deepfake Detection Across Multi-modalities: A Comprehensive SurveyyHong-Hanh Nguyen-Le, Van-Tuan Tran, Dinh-Thuc Nguyen, and Nhien-An Le-KhacAuthorea Preprints, 2024
In recent years, deepfakes (DFs) have been utilized for malicious purposes, such as individual impersonation, misinformation spreading, and artists style imitation, raising questions about ethical and security concerns. In this survey, we provide a comprehensive review and comparison of passive DF detection across multiple modalities, including image, video, audio, and multi-modal, to explore the inter-modality relationships between them. Beyond detection accuracy, we extend our analysis to encompass crucial performance dimensions essential for real-world deployment: generalization capabilities across novel generation techniques, robustness against adversarial manipulations and postprocessing techniques, attribution precision in identifying generation sources, and resilience under real-world operational conditions. Additionally, we analyze the advantages and limitations of existing datasets, benchmarks, and evaluation metrics for passive DF detection. Finally, we propose future research directions that address these unexplored and emerging issues in the field of passive DF detection. This survey offers researchers and practitioners a comprehensive resource for understanding the current landscape, methodological approaches, and promising future directions in this rapidly evolving field.