Honggang Liu

Honggang Liu

Auto-generated profile, based on publicly available information

Honggang Liu

School of Computer Science, Hangzhou Dianzi University, Hangzhou, Zhejiang, China

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
20 May 2025 in ACM Transactions on Multimedia Computing, Communications, and Applications
Verified
Journal Article
Open access
DLDongjun Liu
Dongjun Liu
WDWeichen Dai
Weichen Dai
HLHonggang Liu
Honggang Liu
HYHangjie Yi
Hangjie Yi
Wanzeng KongWanzeng Kong
Wanzeng Kong
Recent works on visual classification tasks have leveraged EEG signals to provide additional supervisory information, further improving the performance of the models on natural images. However, previous methods often force machine models to directly match EEG signals, which involves the transfer of modal-specific representations, leading to potentially distorted alignment of modal-shared representations. Moreover, focusing solely on aligning individual sample features neglects the alignment of relationships between samples, making it difficult to capture the potential relational reasoning capabilities in EEG signals. This relational reasoning ability is key to the human brain's outstanding performance in visual classification tasks. Similarly, for a machine model, the complex relationships between instances are more critical than individual instances. Inspired by this, our idea is to enhance machine visual classification capabilities by imparting human-like relational reasoning, encouraging machine models to focus on the relational structure within EEG signals. To this end, we propose a brain-machine relation alignment method that constructs a cognitive model and a visual model to process EEG signals and visual images, respectively. Instead of forcing the visual model to mimic the output of an individual EEG data sample represented by the cognitive model, we encourage it to learn the mutual relations of EEG data samples. By penalizing the difference in relational structures between EEG signals and visual images, we facilitate the transfer of relational knowledge. Experiments demonstrate that the proposed method significantly improves the classification performance of the visual model. This highlights the potential of relational alignment as a robust mechanism for integrating human relational reasoning into machine learning models.

1 September 2025 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
HLHonggang Liu
Honggang Liu
HYHan Yang
Han Yang
DLDongjun Liu
Dongjun Liu
XJXuanyu Jin
Xuanyu Jin
Yong PengYong Peng
Yong Peng
Wanzeng KongWanzeng Kong
Wanzeng Kong
Biometric recognition using visually evoked potentials (VEPs), a type of neural response to visual stimuli recorded via electroencephalography (EEG), has shown great promise. However, the non-stationary nature of EEG signals poses a major challenge in cross-session scenarios, where data collected on different days often leads to performance degradation. To address this, we propose the Discriminative Robust Feature Network (DRFNet) to enhance the robustness and inter-subject discriminability of identity representations across sessions. DRFNet incorporates two key components: (1) A log-power transformation that amplifies inter-individual differences by capturing non-linear energy patterns from VEP features via signal squaring and logarithmic scaling; and (2) A hierarchical normalization strategy with adaptive attention to balance discriminative identity cues with inter-session invariance by stabilizing feature distributions across multiple levels (feature map, batch, and sample). On two public multi-session SSVEP datasets (Dataset A: 30 subjects, 6 s trials; Dataset B: 54 subjects, 4 s trials), our model outperformed state-of-the-art methods, achieving identification accuracies of 92.92% and 86.30%, and equal error rates of 3.92% and 4.09%, respectively. Further analysis demonstrates that filter bank processing and a reduced set of parietal-occipital electrodes can provide more discriminative features while offering a practical path toward system lightweighting. The code is available at: https://github.com/Ultramua/DRFNet.git.

10 July 2025 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
HLHonggang Liu
Honggang Liu
HYHan Yang
Han Yang
DLDongjun Liu
Dongjun Liu
HYHangjie Yi
Hangjie Yi
BHBingfeng He
Bingfeng He
Wanzeng KongWanzeng Kong
Wanzeng Kong
Visual evoked potential (VEP)-based EEG biometrics provide a secure, spoof-resistant approach for identification and authentication; however, cross-session variability, driven by temporal fluctuations in neural responses, often undermines feature stability and degrades performance. To tackle this, we propose the Dual Attention Refinement Network (DARN), a novel method that enhances the spatiotemporal consistency of EEG representations without requiring frequent retraining. DARN combines a lightweight CNN backbone with two complementary attention modules: the Spatial Feature Refinement Unit (SFRU), which prioritizes consistent spatial patterns, and the Inter-channel Refinement Unit (ICRU), which captures stable inter-channel dependencies, jointly refining the spatial and channel dimensions of extracted EEG feature maps. Evaluated on two public multi-session VEP datasets with 30 and 54 subjects, with sample durations of 6 seconds for the 30-class dataset and 4 seconds for the 54-class dataset, DARN surpasses state-of-the-art baselines, achieving identification accuracies of 93.83% (30 classes) and 84.55% (54 classes), and authentication equal error rates of 3.05% and 3.85%, respectively. Moreover, our analysis highlights the pivotal role of visual stimulus diversity in improving cross-session generalization, offering practical insights for designing robust VEP-based biometric systems. The source code is available at https://github.com/Ultramua/DARN.

6 August 2025 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
Yong PengYong Peng
Yong Peng
JLJiangchuan Liu
Jiangchuan Liu
HLHonggang Liu
Honggang Liu
NPNatasha Padfield
Natasha Padfield
JLJunhua Li
Junhua Li
ACAndrzej Cichocki
Andrzej Cichocki
Domain adaptation has proven effective for suppressing the inter-subject variability problem in cross-subject EEG classification tasks in which labeled data is available for source subjects while only unlabeled data is provided for target subjects. Existing domain adaptation methods typically reduced the distribution discrepancy between source and target domains by directly utilizing source domain samples or features. To safeguard the privacy of source domain data, we propose to construct a Proxy Domain by simultaneously considering the prediction Consistency and Confidence (PDCC) of locally trained source models on target EEG samples, serving as the substitute to the source domain. The framework commences with the augmentation and alignment of the source domain data to enhance feature generalizability, after which source models are trained independently on each source subject's data in a decentralized manner. Knowledge transfer from source to target domains is achieved exclusively through accessing to the source domain model, enabling the PDCC-based proxy domain construction that encapsulates the source knowledge. Finally, domain adaptation is performed using the proxy domain and target domain. As a result, PDCC eliminates the need to access source domain data while effectively leveraging source knowledge. Experimental results on four benchmark EEG datasets demonstrate that PDCC consistently outperforms eleven existing methods, including several advanced transfer learning and source-free methods. Especially, the effectiveness of the proxy domain is extensively investigated. The source code for reproducing the experimental results is available from https://github.com/SunseaIU/PDCC.

23 February 2026 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
HYHan Yang
Han Yang
ZCZhe Chen
Zhe Chen
YSYiwen Shen
Yiwen Shen
HLHonggang Liu
Honggang Liu
Wanzeng KongWanzeng Kong
Wanzeng Kong
Recent advances in underwater sonar detection have highlighted the challenges of acquiring real-world sonar data due to experimental costs and environmental constraints. While deep learning-based methods have shown promise in sonar synthesis, existing approaches often lack fidelity in waveform generation. This manuscript proposes Multi-Band HiFi-GAN, a high-fidelity synthesis method that incorporates a multi-band processing module based on a Pseudo-QMF bank for spectrally-efficient sub-band decomposition, and Multi-Band STFT Discriminator (MBSD) that jointly models time-frequency structures and mitigates aliasing artifacts. Additionally, we design a multi-resolution STFT loss to enhance convergence. Evaluated on DeepShip dataset using Fréchet Audio Distance (FAD), our method demonstrates superior performance, achieving a lower FAD score than existing approaches. Augmenting real training data with synthesized samples improves target classification accuracy to 96.94% at a 100% mixing ratio. The work provides a practical data augmentation solution for underwater acoustic systems, improving synthesis fidelity.

22 April 2025 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
JQJingsheng Qian
Jingsheng Qian
HYHangjie Yi
Hangjie Yi
HLHonggang Liu
Honggang Liu
XJXuanyu Jin
Xuanyu Jin
Wanzeng KongWanzeng Kong
Wanzeng Kong
While various deep learning techniques for electroencephalogram (EEG)-based brainprint recognition have achieved considerable success, these models remain vulnerable to adversarial attacks. However, existing black-box attack methods suffer from an inherent trade-off between query efficiency and distortion level. To address this challenge and further investigate the security risks of brainprint recognition systems in real-world black-box scenarios, we propose a query-efficient, low-distortion black-box attack method that targets the high-frequency components of EEG signals. Our approach innovatively selects sparse sampling points to estimate more accurate gradient information and leverages historical gradients to guide the prioritization of important points, thereby accelerating the attack process. The perturbations are applied in the high-frequency domain of the EEG signal to enhance stealth and effectiveness. Extensive experiments under black-box settings demonstrate that our method achieves state-of-the-art performance across two datasets and four models. Compared to existing methods, our approach significantly improves attack success rates while reducing the number of queries and minimizing distortion to imperceptible levels, thus achieving a superior balance between query efficiency and perturbation stealth.