Kejia Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Kejia Chen has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Jiazhen Yang
Zhejiang University, Hangzhou, China
3 shared publications - Zunlei Feng
Zhejiang University, Hangzhou, China
3 shared publications - Bingde Hu
Zhejiang University, Hangzhou, China
2 shared publications Jiawen Zhang
2 shared publications- Yang Gao
Zhejiang University, Hangzhou, China
2 shared publications - Dan Li
Sun Yat-sen University, Zhuhai, Guangdong, China
1 shared publication
Latest Publications
- Open Access
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1312-1326
Understanding and Preserving Safety in Fine-Tuned LLMs
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1312-1326
Open AccessUnderstanding and Preserving Safety in Fine-Tuned LLMs
- 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.
- 7 February 2026
- Published by Elsevier in Pattern Recognition
- Vol. 176
Self-improved holistic alignment for preference enhancement
- 7 February 2026
- Published by Elsevier in Pattern Recognition
- Vol. 176
Self-improved holistic alignment for preference enhancement
- Open Access
- 5 January 2025
- Published by Elsevier in Blockchain: Research and Applications
- Vol. 6 (2)
πFL: Private, atomic, incentive mechanism for federated learning based on blockchain
- 5 January 2025
- Published by Elsevier in Blockchain: Research and Applications
- Vol. 6 (2)
Open AccessπFL: Private, atomic, incentive mechanism for federated learning based on blockchain