Author name cluster

Huy Phan

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

14 papers

2 author rows

TMLR Journal 2025 Journal Article

DisDet: Exploring Detectability of Backdoor Attack on Diffusion Models

Yang Sui
Huy Phan
Jinqi Xiao
Tianfang Zhang
Zijie Tang
Cong Shi
Yan Wang
Yingying Chen

In the exciting generative AI era, the diffusion model has emerged as a very powerful and widely adopted content-generation tool. Very recently, some pioneering works have shown the vulnerability of the diffusion model against backdoor attacks, calling for in-depth analysis and investigation of the security challenges. In this paper, we explore the detectability of the poisoned noise input for the backdoored diffusion models, an important performance metric yet little explored in the existing works. Starting from the perspective of a defender, we first analyze the distribution discrepancy of the trigger pattern in the existing diffusion backdoor attacks. Based on this finding, we propose a trigger detection mechanism that can effectively identify the poisoned input noise. Then, from the attack side, we propose a backdoor attack strategy that can learn the unnoticeable trigger to evade our proposed detection scheme. Our empirical evaluations across various diffusion models and datasets demonstrate the effectiveness of the proposed trigger detection and detection-evading attack strategy. For trigger detection, our distribution discrepancy-based solution can achieve a 100% detection rate for the Trojan triggers used in the existing works. For evading trigger detection, our proposed stealthy trigger design approach performs end-to-end learning to make the distribution of poisoned noise input approach that of benign noise, enabling nearly 100% detection pass rate with very high attack and benign performance for the backdoored diffusion models.

PDF Details

JBHI Journal 2025 Journal Article

DSleepNet: Disentanglement Learning for Personal Attribute-Agnostic Three-Stage Sleep Classification Using Wearable Sensing Data

Bing Zhai
Haoran Duan
Yu Guan
Huy Phan
Wai Lok Woo

Long-term non-invasive sleep stage monitoring is instrumental in comprehending the progression of sleep disorders, cardiovascular diseases, and the interplay between sleep, type 2 diabetes, and neurodegenerative diseases. However, the conventional deep learning approach is susceptible to personal attributes (PAs) such as age, Body Mass Index, and severity of sleep apnea existing in the training dataset, potentially hindering its generalisation capacity to unseen cohorts. This paper introduces DSleepNet, a novel approach that disentangles the feature space into PA-specific and PA-agnostic components using two probabilistic encoders. The PA-agnostic features, designed to remain unaffected by personal attributes, outperformed the baseline CNN, improving the mean F1 score by up to 8. 7% (baseline: 60. 3) and Cohen's Kappa by 4. 7% (baseline: 55. 5), especially in reducing the impact of sleep apnea. DSleepNet functions without the need for target cohort data during training. It operates without the need to acquire PA data during inference, nor does it require fine-tuning. A novel Independent Excitation mechanism is incorporated into the latent feature space to remove correlations between the two types of features. Comprehensive testing in various PA settings has demonstrated its efficacy in improving the model's robustness.

Details DOI

ICML Conference 2025 Conference Paper

Generative Audio Language Modeling with Continuous-valued Tokens and Masked Next-Token Prediction

Shu-Wen Yang
Byeonggeun Kim
Kuan-Po Huang
Qingming Tang
Huy Phan
Bo-Ru Lu
Harshavardhan Sundar
Shalini Ghosh

Autoregressive next-token prediction with the Transformer decoder has become a de facto standard in large language models (LLMs), achieving remarkable success in Natural Language Processing (NLP) at scale. Extending this paradigm to audio poses unique challenges due to its inherently continuous nature. We research audio generation with a causal language model (LM) without discrete tokens. We leverage token-wise diffusion to model the continuous distribution of the next continuous-valued token. Our approach delivers significant improvements over previous discrete solution, AudioGen, achieving 20% and 40% relative gains on AudioCaps in Frechet Audio Distance (FAD) and Kullback-Leibler (KL) divergence, respectively. Additionally, we propose a novel masked next-token prediction task that incorporates masked prediction into the causal LM framework. On AudioCaps, the innovation yields 41% and 33% relative FAD improvements over AudioGen Base (285M) and AudioGen Large (1B) models, respectively, and is on par with the state-of-the-art (SOTA) diffusion models. Furthermore, we achieve these results with significantly fewer parameters—193M for our Base and 462M for our Large models.

Details

ICML Conference 2025 Conference Paper

IMPACT: Iterative Mask-based Parallel Decoding for Text-to-Audio Generation with Diffusion Modeling

Kuan-Po Huang
Shu-Wen Yang
Huy Phan
Bo-Ru Lu
Byeonggeun Kim
Sashank Macha
Qingming Tang
Shalini Ghosh

Text-to-audio generation synthesizes realistic sounds or music given a natural language prompt. Diffusion-based frameworks, including the Tango and the AudioLDM series, represent the state-of-the-art in text-to-audio generation. Despite achieving high audio fidelity, they incur significant inference latency due to the slow diffusion sampling process. MAGNET, a mask-based model operating on discrete tokens, addresses slow inference through iterative mask-based parallel decoding. However, its audio quality still lags behind that of diffusion-based models. In this work, we introduce IMPACT, a text-to-audio generation framework that achieves high performance in audio quality and fidelity while ensuring fast inference. IMPACT utilizes iterative mask-based parallel decoding in a continuous latent space powered by diffusion modeling. This approach eliminates the fidelity constraints of discrete tokens while maintaining competitive inference speed. Results on AudioCaps demonstrate that IMPACT achieves state-of-the-art performance on key metrics including Fréchet Distance (FD) and Fréchet Audio Distance (FAD) while significantly reducing latency compared to prior models. The project website is available at https: //audio-impact. github. io/.

Details

JBHI Journal 2025 Journal Article

Subject-Adaptation Salient Wave Detection Network for Multimodal Sleep Stage Classification

Jing Wang
Xuehui Wang
Xiaojun Ning
Youfang Lin
Huy Phan
Ziyu Jia

Sleep stage classification is an important step in the diagnosis and treatment of sleep disorders. Despite the high classification performance of previous sleep stage classification work, some challenges remain unresolved: 1) How to effectively capture salient waves in sleep signals to improve sleep stage classification results. 2) How to capture salient waves affected by inter-subject variability. 3) How to adaptively regulate the importance of different modals for different sleep stages. To address these challenges, we propose SleepWaveNet, a multimodal salient wave detection network, which is motivated by the salient object detection task in computer vision. It has a U-Transformer structure to detect salient waves in sleep signals. Meanwhile, the subject-adaptation wave extraction architecture based on transfer learning can adapt to the information of target individuals and extract salient waves with inter-subject variability. In addition, the multimodal attention module can adaptively enhance the importance of specific modal data for sleep stage classification tasks. Experiments on three datasets show that SleepWaveNet has better overall performance than existing baselines. Moreover, visualization experiments show that the model has the ability to capture salient waves with inter-subject variability.

Details DOI

AAAI Conference 2023 Conference Paper

CSTAR: Towards Compact and Structured Deep Neural Networks with Adversarial Robustness

Huy Phan
Miao Yin
Yang Sui
Bo Yuan
Saman Zonouz

Model compression and model defense for deep neural networks (DNNs) have been extensively and individually studied. Considering the co-importance of model compactness and robustness in practical applications, several prior works have explored to improve the adversarial robustness of the sparse neural networks. However, the structured sparse models obtained by the existing works suffer severe performance degradation for both benign and robust accuracy, thereby causing a challenging dilemma between robustness and structuredness of compact DNNs. To address this problem, in this paper, we propose CSTAR, an efficient solution that simultaneously impose Compactness, high STructuredness and high Adversarial Robustness on the target DNN models. By formulating the structuredness and robustness requirement within the same framework, the compressed DNNs can simultaneously achieve high compression performance and strong adversarial robustness. Evaluations for various DNN models on different datasets demonstrate the effectiveness of CSTAR. Compared with the state-of-the-art robust structured pruning, CSTAR shows consistently better performance. For instance, when compressing ResNet-18 on CIFAR-10, CSTAR achieves up to 20.07% and 11.91% improvement for benign accuracy and robust accuracy, respectively. For compressing ResNet-18 with 16x compression ratio on Imagenet, CSTAR obtains 8.58% benign accuracy gain and 4.27% robust accuracy gain compared to the existing robust structured pruning.

PDF Details DOI

JBHI Journal 2023 Journal Article

L-SeqSleepNet: Whole-cycle Long Sequence Modeling for Automatic Sleep Staging

Huy Phan
Kristian P. Lorenzen
Elisabeth Heremans
Oliver Y. Chén
Minh C. Tran
Philipp Koch
Alfred Mertins
Mathias Baumert

Human sleep is cyclical with a period of approximately 90 minutes, implying long temporal dependency in the sleep data. Yet, exploring this long-term dependency when developing sleep staging models has remained untouched. In this work, we show that while encoding the logic of a whole sleep cycle is crucial to improve sleep staging performance, the sequential modelling approach in existing state-of-the-art deep learning models are inefficient for that purpose. We thus introduce a method for efficient long sequence modelling and propose a new deep learning model, L-SeqSleepNet, which takes into account whole-cycle sleep information for sleep staging. Evaluating L-SeqSleepNet on four distinct databases of various sizes, we demonstrate state-of-the-art performance obtained by the model over three different EEG setups, including scalp EEG in conventional Polysomnography (PSG), in-ear EEG, and around-the-ear EEG (cEEGrid), even with a single EEG channel input. Our analyses also show that L-SeqSleepNet is able to alleviate the predominance of N2 sleep (the major class in terms of classification) to bring down errors in other sleep stages. Moreover the network becomes much more robust, meaning that for all subjects where the baseline method had exceptionally poor performance, their performance are improved significantly. Finally, the computation time only grows at a sub-linear rate when the sequence length increases.

Details DOI

JBHI Journal 2023 Journal Article

Personalized Longitudinal Assessment of Multiple Sclerosis Using Smartphones

Oliver Y. Chén
Florian Lipsmeier
Huy Phan
Frank Dondelinger
Andrew Creagh
Christian Gossens
Michael Lindemann
Maarten De Vos

Personalized longitudinal disease assessment is central to quickly diagnosing, appropriately managing, and optimally adapting the therapeutic strategy of multiple sclerosis (MS). It is also important for identifying idiosyncratic subject-specific disease profiles. Here, we design a novel longitudinal model to map individual disease trajectories in an automated way using smartphone sensor data that may contain missing values. First, we collect digital measurements related to gait and balance, and upper extremity functions using sensor-based assessments administered on a smartphone. Next, we treat missing data via imputation. We then discover potential markers of MS by employing a generalized estimation equation. Subsequently, parameters learned from multiple training datasets are ensembled to form a simple, unified longitudinal predictive model to forecast MS over time in previously unseen people with MS. To mitigate potential underestimation for individuals with severe disease scores, the final model incorporates additional subject-specific fine-tuning using data from the first day. The results show that the proposed model is promising to achieve personalized longitudinal MS assessment; they also suggest that features related to gait and balance as well as upper extremity function, remotely collected from sensor-based assessments, may be useful digital markers for predicting MS over time.

Details DOI

AAAI Conference 2022 Conference Paper

BATUDE: Budget-Aware Neural Network Compression Based on Tucker Decomposition

Miao Yin
Huy Phan
Xiao Zang
Siyu Liao
Bo Yuan

Model compression is very important for the efficient deployment of deep neural network (DNN) models on resourceconstrained devices. Among various model compression approaches, high-order tensor decomposition is particularly attractive and useful because the decomposed model is very small and fully structured. For this category of approaches, tensor ranks are the most important hyper-parameters that directly determine the architecture and task performance of the compressed DNN models. However, as an NP-hard problem, selecting optimal tensor ranks under the desired budget is very challenging and the state-of-the-art studies suffer from unsatisfied compression performance and timing-consuming search procedures. To systematically address this fundamental problem, in this paper we propose BATUDE, a Budget- Aware TUcker DEcomposition-based compression approach that can efficiently calculate optimal tensor ranks via oneshot training. By integrating the rank selecting procedure to the DNN training process with a specified compression budget, the tensor ranks of the DNN models are learned from the data and thereby bringing very significant improvement on both compression ratio and classification accuracy for the compressed models. The experimental results on ImageNet dataset show that our method enjoys 0. 33% top-5 higher accuracy with 2. 52× less computational cost as compared to the uncompressed ResNet-18 model. For ResNet-50, the proposed approach enables 0. 37% and 0. 55% top-5 accuracy increase with 2. 97× and 2. 04× computational cost reduction, respectively, over the uncompressed model.

PDF Details

NeurIPS Conference 2021 Conference Paper

CHIP: CHannel Independence-based Pruning for Compact Neural Networks

Yang Sui
Miao Yin
Yi Xie
Huy Phan
Saman Aliari Zonouz
Bo Yuan

Filter pruning has been widely used for neural network compression because of its enabled practical acceleration. To date, most of the existing filter pruning works explore the importance of filters via using intra-channel information. In this paper, starting from an inter-channel perspective, we propose to perform efficient filter pruning using Channel Independence, a metric that measures the correlations among different feature maps. The less independent feature map is interpreted as containing less useful information$/$knowledge, and hence its corresponding filter can be pruned without affecting model capacity. We systematically investigate the quantification metric, measuring scheme and sensitiveness$/$reliability of channel independence in the context of filter pruning. Our evaluation results for different models on various datasets show the superior performance of our approach. Notably, on CIFAR-10 dataset our solution can bring $0. 75\%$ and $0. 94\%$ accuracy increase over baseline ResNet-56 and ResNet-110 models, respectively, and meanwhile the model size and FLOPs are reduced by $42. 8\%$ and $47. 4\%$ (for ResNet-56) and $48. 3\%$ and $52. 1\%$ (for ResNet-110), respectively. On ImageNet dataset, our approach can achieve $40. 8\%$ and $44. 8\%$ storage and computation reductions, respectively, with $0. 15\%$ accuracy increase over the baseline ResNet-50 model. The code is available at https: //github. com/Eclipsess/CHIP_NeurIPS2021.

PDF Details

JBHI Journal 2021 Journal Article

CNN-MoE Based Framework for Classification of Respiratory Anomalies and Lung Disease Detection

Lam Pham
Huy Phan
Ramaswamy Palaniappan
Alfred Mertins
Ian McLoughlin

This paper presents and explores a robust deep learning framework for auscultation analysis. This aims to classify anomalies in respiratory cycles and detect diseases, from respiratory sound recordings. The framework begins with front-end feature extraction that transforms input sound into a spectrogram representation. Then, a back-end deep learning network is used to classify the spectrogram features into categories of respiratory anomaly cycles or diseases. Experiments, conducted over the ICBHI benchmark dataset of respiratory sounds, confirm three main contributions towards respiratory-sound analysis. Firstly, we carry out an extensive exploration of the effect of spectrogram types, spectral-time resolution, overlapping/non-overlapping windows, and data augmentation on final prediction accuracy. This leads us to propose a novel deep learning system, built on the proposed framework, which outperforms current state-of-the-art methods. Finally, we apply a Teacher-Student scheme to achieve a trade-off between model performance and model complexity which holds promise for building real-time applications.

Details DOI

YNIMG Journal 2021 Journal Article

Identifying neural signatures mediating behavioral symptoms and psychosis onset: High-dimensional whole brain functional mediation analysis

Oliver Y. Chén
Hengyi Cao
Huy Phan
Guy Nagels
Jenna M. Reinen
Jiangtao Gou
Tianchen Qian
Junrui Di

Along the pathway from behavioral symptoms to the development of psychotic disorders sits the multivariate mediating brain. The functional organization and structural topography of large-scale multivariate neural mediators among patients with brain disorders, however, are not well understood. Here, we design a high-dimensional brain-wide functional mediation framework to investigate brain regions that intermediate between baseline behavioral symptoms and future conversion to full psychosis among individuals at clinical high risk (CHR). Using resting-state functional magnetic resonance imaging (fMRI) data from 263 CHR subjects, we extract an α brain atlas and a β brain atlas: the former underlines brain areas associated with prodromal symptoms and the latter highlights brain areas associated with disease onset. In parallel, we identify and separate mediators that potentially positively and negatively mediate symptoms and psychosis, respectively, and quantify the effect of each neural mediator on disease development. Taken together, these results paint a brain-wide picture of neural markers that are potentially mediating behavioral symptoms and the development of psychotic disorders; additionally, they underscore a statistical framework that is useful to uncover large-scale intermediating variables in a regulatory biological system.

Details DOI

JBHI Journal 2021 Journal Article

MetaSleepLearner: A Pilot Study on Fast Adaptation of Bio-Signals-Based Sleep Stage Classifier to New Individual Subject Using Meta-Learning

Nannapas Banluesombatkul
Pichayoot Ouppaphan
Pitshaporn Leelaarporn
Payongkit Lakhan
Busarakum Chaitusaney
Nattapong Jaimchariyatam
Ekapol Chuangsuwanich
Wei Chen

Identifying bio-signals based-sleep stages requires time-consuming and tedious labor of skilled clinicians. Deep learning approaches have been introduced in order to challenge the automatic sleep stage classification conundrum. However, the difficulties can be posed in replacing the clinicians with the automatic system due to the differences in many aspects found in individual bio-signals, causing the inconsistency in the performance of the model on every incoming individual. Thus, we aim to explore the feasibility of using a novel approach, capable of assisting the clinicians and lessening the workload. We propose the transfer learning framework, entitled MetaSleepLearner, based on Model Agnostic Meta-Learning (MAML), in order to transfer the acquired sleep staging knowledge from a large dataset to new individual subjects (source code is available at https://github.com/IoBT-VISTEC/MetaSleepLearner). The framework was demonstrated to require the labelling of only a few sleep epochs by the clinicians and allow the remainder to be handled by the system. Layer-wise Relevance Propagation (LRP) was also applied to understand the learning course of our approach. In all acquired datasets, in comparison to the conventional approach, MetaSleepLearner achieved a range of 5. 4% to 17. 7% improvement with statistical difference in the mean of both approaches. The illustration of the model interpretation after the adaptation to each subject also confirmed that the performance was directed towards reasonable learning. MetaSleepLearner outperformed the conventional approaches as a result from the fine-tuning using the recordings of both healthy subjects and patients. This is the first work that investigated a non-conventional pre-training method, MAML, resulting in a possibility for human-machine collaboration in sleep stage classification and easing the burden of the clinicians in labelling the sleep stages through only several epochs rather than an entire recording.

Details DOI

AAAI Conference 2020 Conference Paper

CAG: A Real-Time Low-Cost Enhanced-Robustness High-Transferability Content-Aware Adversarial Attack Generator

Huy Phan
Yi Xie
Siyu Liao
Jie Chen
Bo Yuan

Deep neural networks (DNNs) are vulnerable to adversarial attack despite their tremendous success in many artiﬁcial intelligence ﬁelds. Adversarial attack is a method that causes the intended misclassﬁcation by adding imperceptible perturbations to legitimate inputs. To date, researchers have developed numerous types of adversarial attack methods. However, from the perspective of practical deployment, these methods suffer from several drawbacks such as long attack generating time, high memory cost, insufﬁcient robustness and low transferability. To address the drawbacks, we propose a Content-aware Adversarial Attack Generator (CAG) to achieve real-time, low-cost, enhanced-robustness and hightransferability adversarial attack. First, as a type of generative model-based attack, CAG shows signiﬁcant speedup (at least 500 times) in generating adversarial examples compared to the state-of-the-art attacks such as PGD and C&W. Furthermore, CAG only needs a single generative model to perform targeted attack to any targeted class. Because CAG encodes the label information into a trainable embedding layer, it differs from prior generative model-based adversarial attacks that use n different copies of generative models for n different targeted classes. As a result, CAG signiﬁcantly reduces the required memory cost for generating adversarial examples. Moreover, CAG can generate adversarial perturbations that focus on the critical areas of input by integrating the class activation maps information in the training process, and hence improve the robustness of CAG attack against the state-of-art adversarial defenses. In addition, CAG exhibits high transferability across different DNN classiﬁer models in black-box attack scenario by introducing random dropout in the process of generating perturbations. Extensive experiments on different datasets and DNN models have veriﬁed the realtime, low-cost, enhanced-robustness, and high-transferability beneﬁts of CAG.

PDF Details