Jiantao Xu

Dr. Jiantao Xu

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
JXJiantao Xu
Jiantao Xu
CZChen Zhang
Chen Zhang
LJLiu Jin
Liu Jin
Chunhua SuChunhua Su
Chunhua Su
Federated learning enables privacy-preserving model training across distributed clients, yet real-world deployments face statistical, system, and behavioral heterogeneity, which degrades performance and increases vulnerability to adversarial clients. Existing incentive mechanisms often neglect participant credibility, leading to unfair rewards and reduced robustness. To address these issues, we propose a Trust-Aware Incentive Mechanism (TAIM), which evaluates client reliability through a multi-dimensional trust model incorporating participation frequency, gradient consistency, and contribution effectiveness. A trust-weighted reward allocation is formulated via a Stackelberg game, and a confidence-based soft filtering algorithm is introduced to mitigate the impact of unreliable updates. Experiments on FEMNIST, CIFAR-10, and Sent140 demonstrate that TAIM improves accuracy by up to 4.1%, reduces performance degradation under adaptive attacks by over 35%, and ensures fairer incentive distribution with a Gini coefficient below 0.3. TAIM offers a robust and equitable FL framework suitable for heterogeneous edge environments.

21 August 2024 in Mathematics
Verified
Journal Article
Open access
PDF file
HWHaoda Wang
Haoda Wang
CQChen QIU
Chen QIU
CZChen Zhang
Chen Zhang
JXJiantao Xu
Jiantao Xu
Chunhua SuChunhua Su
Chunhua Su
With the development of edge computing and deep learning, intelligent human behavior recognition has spawned extensive applications in smart worlds. However, current edge computing technology faces performance bottlenecks due to limited computing resources at the edge, which prevent deploying advanced deep neural networks. In addition, there is a risk of privacy leakage during interactions between the edge and the server. To tackle these problems, we propose an effective, privacy-preserving edge–cloud collaborative interaction scheme based on WiFi, named P-CA, for human behavior sensing. In our scheme, a convolutional autoencoder neural network is split into two parts. The shallow layers are deployed on the edge side for inference and privacy-preserving processing, while the deep layers are deployed on the server side to leverage its computing resources. Experimental results based on datasets collected from real testbeds demonstrate the effectiveness and considerable performance of the P-CA. The recognition accuracy can maintain 88%, although it could achieve about 94.8% without the mixing operation. In addition, the proposed P-CA achieves better recognition accuracy than two state-of-the-art methods, i.e., FedLoc and PPDFL, by 2.7% and 2.1%, respectively, while maintaining privacy.

11 August 2025 in Telecom
Verified
Journal Article
Open access
PDF file
YCYixuan Cai
Yixuan Cai
JXJianbo Xu
Jianbo Xu
ZLZhuotao Lian
Zhuotao Lian
BKBrian Chi Wing KEI
Brian Chi Wing KEI
YLYuxing Li
Yuxing Li
JXJiantao Xu
Jiantao Xu
Federated Learning (FL) enables privacy-preserving model training across distributed clients. However, its reliance on voluntary client participation makes it vulnerable to strategic behaviors—actions that are not overtly malicious but significantly impair model convergence and fairness. Existing defense methods primarily focus on explicit attacks, overlooking the challenges posed by economically motivated “pseudo-honest” clients. To address this gap, we propose a Reputation-Aware Defense Framework to mitigate strategic behaviors in FL. This framework introduces a multi-dimensional dynamic reputation model that evaluates client behaviors based on gradient alignment, participation consistency, and update stability. The resulting reputation scores are incorporated into both aggregation and incentive mechanisms, forming a behavior-feedback loop that rewards honest participation and penalizes opportunistic strategies. We theoretically prove the convergence of reputation scores, the suppression of low-quality updates in aggregation, and the emergence of honest participation as a Nash equilibrium under the incentive mechanism. Experiments on datasets such as CIFAR-10, FEMNIST, MIMIC-III demonstrate that our approach significantly outperforms baseline methods in accuracy, fairness, and robustness, even when up to 60% of clients act strategically. This study bridges trust modeling and robust optimization in FL, offering a secure foundation for federated systems operating in open and incentive-driven environments.

26 September 2025 in Electronics
Verified
Journal Article
Open access
PDF file
JXJiantao Xu
Jiantao Xu
LJLiu Jin
Liu Jin
Chunhua SuChunhua Su
Chunhua Su
The proliferation of Internet of Things (IoT) devices has created a distributed ecosystem where users generate vast amounts of review data across heterogeneous platforms, from smart home assistants to connected vehicles. This data is crucial for service improvement but is plagued by fake reviews, data quality inconsistencies, and significant privacy risks. Traditional centralized analytics fail in this landscape due to data privacy regulations and the sheer scale of distributed data. To address this, we propose FedDQ, a federated learning framework for Privacy-Preserving Federated Review Analytics with Data Quality Optimization. FedDQ introduces a multi-faceted data quality assessment module that operates locally on each IoT device, evaluating review data based on textual coherence, behavioral patterns, and cross-modal consistency without exposing raw data. These quality scores are then used to orchestrate a quality-aware aggregation mechanism at the server, prioritizing contributions from high-quality, reliable clients. Furthermore, our framework incorporates differential privacy and models system heterogeneity to ensure robustness and practical applicability in resource-constrained IoT environments. Extensive experiments on multiple real-world datasets show that FedDQ significantly outperforms baseline federated learning methods in accuracy, convergence speed, and resilience to data poisoning attacks, achieving up to a 13.8% improvement in F1-score under highly heterogeneous and noisy conditions while preserving user privacy.