Bingde Hu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Bingde Hu has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Mingli Song
Zhejiang University, Hangzhou, China
3 shared publications - Xinyu Wang
Zhejiang University, Hangzhou, China
3 shared publications - Zunlei Feng
Zhejiang University, Hangzhou, China
3 shared publications - Jiazhen Yang
Zhejiang University, Hangzhou, China
2 shared publications - Kejia Chen
Zhejiang University, Hangzhou, China
2 shared publications - Tongya Zheng
Hangzhou City University, Hangzhou, China
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 13193-13202
Adaptive Forensic Feature Refinement via Intrinsic Importance Perception
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 13193-13202
Open AccessAdaptive Forensic Feature Refinement via Intrinsic Importance Perception
- Open Access
- 20 April 2026
- Published by Elsevier in SSRN Electronic Journal
An Effective Stochastic Response Entropy Criterion for Model Poisoning Detection in Federated Learning
Federated Learning (FL) is vulnerable to model poisoning attacks, where malicious clients directly manipulate local gradient to corrupt global model optimization. Existing methods typically rely on task-relevant validation data or impose strict assumptions on data distributions, and therefore struggle to effectively distinguish malicious gradients from outlying benign gradients caused by data heterogeneity in privacy-constrained real world Non-IID scenarios. In this work, we investigate the fundamental differences in predictive behavior between malicious and benign models from the perspective of random data. Our key observation indicates that malicious models exhibit pronounced prediction bias when evaluated on random data due to tampering with local updates, whereas benign models are driven by prior knowledge and yield more diverse predictions. This provides a novel perspective for defending against model poisoning attacks beyond traditional gradient space analysis. To quantify this behavioral discrepancy, we introduce Stochastic Response Entropy, an entropy-based criterion that measures the diversity of model predictions on random data. Building on this insight, we propose FedSRE, a novel defense framework for FL. FedSRE introduces an adaptive robust aggregation strategy that maximizes global model prediction diversity on random data by dynamically adjusting client aggregation weights. Furthermore, FedSRE conducts cluster analysis on learned weights to identify potentially malicious clients and facilitate contribution-based aggregation of benign clients. Experiments across various datasets and attack settings show that FedSRE not only achieves competitive defense performance by effectively detecting malicious clients, but also quantifies the contributions of benign clients to enhance global model performance. The source code is available at this link.
- 20 April 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessAn Effective Stochastic Response Entropy Criterion for Model Poisoning Detection in Federated Learning
Federated Learning (FL) is vulnerable to model poisoning attacks, where malicious clients directly manipulate local gradient to corrupt global model optimization. Existing methods typically rely on task-relevant validation data or impose strict assumptions on data distributions, and therefore struggle to effectively distinguish malicious gradients from outlying benign gradients caused by data heterogeneity in privacy-constrained real world Non-IID scenarios. In this work, we investigate the fundamental differences in predictive behavior between malicious and benign models from the perspective of random data. Our key observation indicates that malicious models exhibit pronounced prediction bias when evaluated on random data due to tampering with local updates, whereas benign models are driven by prior knowledge and yield more diverse predictions. This provides a novel perspective for defending against model poisoning attacks beyond traditional gradient space analysis. To quantify this behavioral discrepancy, we introduce Stochastic Response Entropy, an entropy-based criterion that measures the diversity of model predictions on random data. Building on this insight, we propose FedSRE, a novel defense framework for FL. FedSRE introduces an adaptive robust aggregation strategy that maximizes global model prediction diversity on random data by dynamically adjusting client aggregation weights. Furthermore, FedSRE conducts cluster analysis on learned weights to identify potentially malicious clients and facilitate contribution-based aggregation of benign clients. Experiments across various datasets and attack settings show that FedSRE not only achieves competitive defense performance by effectively detecting malicious clients, but also quantifies the contributions of benign clients to enhance global model performance. The source code is available at this link.
- 2 January 2026
- Published by Elsevier in Journal of Systems and Software
- Vol. 235
RLV: LLM-based vulnerability detection by retrieving and refining contextual information
- 2 January 2026
- Published by Elsevier in Journal of Systems and Software
- Vol. 235
RLV: LLM-based vulnerability detection by retrieving and refining contextual information
- 24 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37 (12) , 7090-7104
Efficient Distributed Graph Neural Network Training With Source Chunking and Moving Aggregation
Graph neural networks (GNNs) are effective models for analyzing graph-structured data, but encounter challenges when training on large distributed graphs. Existing GNN training frameworks use sampling parallelism and historical embedding methods to support distributed training and enhance efficiency. However, these methods suffer from issues like stale historical embeddings, imbalanced communication messages, and redundant storage and computation costs. In this paper, we present Emma, a distributed GNN training framework that incorporates source node centric chunking for frequent updates of embeddings and balanced communication, as well as a moving message aggregation technique to boost training efficiency and reduce storage costs. Experimental results show that Emma significantly enhances training efficiency by reducing computation and communication overhead, leading to a notable speedup while maintaining convergence accuracy compared to state-of-the-art distributed GNN training methods.
- 24 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37 (12) , 7090-7104
Efficient Distributed Graph Neural Network Training With Source Chunking and Moving Aggregation
Graph neural networks (GNNs) are effective models for analyzing graph-structured data, but encounter challenges when training on large distributed graphs. Existing GNN training frameworks use sampling parallelism and historical embedding methods to support distributed training and enhance efficiency. However, these methods suffer from issues like stale historical embeddings, imbalanced communication messages, and redundant storage and computation costs. In this paper, we present Emma, a distributed GNN training framework that incorporates source node centric chunking for frequent updates of embeddings and balanced communication, as well as a moving message aggregation technique to boost training efficiency and reduce storage costs. Experimental results show that Emma significantly enhances training efficiency by reducing computation and communication overhead, leading to a notable speedup while maintaining convergence accuracy compared to state-of-the-art distributed GNN training methods.
- Open Access
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 4494-4506
Disentangled Condensation for Large-scale Graphs
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 4494-4506
Open AccessDisentangled Condensation for Large-scale Graphs
- 22 September 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 35 (9) , 8742-8756
HSDN: A High-Order Structural Semantic Disentangled Neural Network
Graph disentangling is a new promising direction that can help us to discover the latent patterns in the data and understand the behaviors of a graph learning model. Despite the many efforts in disentangling representation learning, few works focus on disentangling the latent factors behind a graph. Most current foci are mainly on studying node-level semantics in the graphs. Compared with node-level, the structure-level view can provide a new interpretable and in-depth insight into graph data. The study of structure-level relations enables us to reveal the high-order structural semantics in the data. To explore the complex high-order structural semantics in the data, we propose the High-order Structural Semantic Disentangled Neural Network (HSDN) to model the graph structure units and disentangle structural semantics. It's the first attempt to hypergraph disentangled networks. Unlike prior methods that disentangle factor graphs based on pair-wise relations only, we introduce hyperedges on pair-wise graphs to model structure units and disentangle the complex high-order structural semantics between different structures. Extensive experiments demonstrate that HSDN achieves state-of-the-art performances in terms of both disentangling and downstream tasks.
- 22 September 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 35 (9) , 8742-8756
HSDN: A High-Order Structural Semantic Disentangled Neural Network
Graph disentangling is a new promising direction that can help us to discover the latent patterns in the data and understand the behaviors of a graph learning model. Despite the many efforts in disentangling representation learning, few works focus on disentangling the latent factors behind a graph. Most current foci are mainly on studying node-level semantics in the graphs. Compared with node-level, the structure-level view can provide a new interpretable and in-depth insight into graph data. The study of structure-level relations enables us to reveal the high-order structural semantics in the data. To explore the complex high-order structural semantics in the data, we propose the High-order Structural Semantic Disentangled Neural Network (HSDN) to model the graph structure units and disentangle structural semantics. It's the first attempt to hypergraph disentangled networks. Unlike prior methods that disentangle factor graphs based on pair-wise relations only, we introduce hyperedges on pair-wise graphs to model structure units and disentangle the complex high-order structural semantics between different structures. Extensive experiments demonstrate that HSDN achieves state-of-the-art performances in terms of both disentangling and downstream tasks.