A5022887194- Blockchain Technology Applications and Security
- Privacy-Preserving Technologies in Data
- Cryptography and Data Security
- IoT and Edge/Fog Computing
- Epigenetics and DNA Methylation
- Genetic Associations and Epidemiology
- Internet of Things and AI
- Domain Adaptation and Few-Shot Learning
- UAV Applications and Optimization
- Brain Tumor Detection and Classification
- Gene expression and cancer classification
- Advanced Graph Neural Networks
- Privacy, Security, and Data Protection
- Security in Wireless Sensor Networks
- Genomics and Rare Diseases
Nanjing University of Science and Technology
2021-2024
University of Chicago
2024
Federated learning (FL), as a distributed machine paradigm, promotes personal privacy by local data processing at each client. However, relying on centralized server for model aggregation, standard FL is vulnerable to malfunctions, untrustworthy servers, and external attacks. To address these issues, we propose decentralized framework integrating blockchain into FL, namely, assisted federated (BLADE-FL). In round of the proposed BLADE-FL, client broadcasts its trained other clients,...
Federated learning (FL), as a distributed machine approach, has drawn great amount of attention in recent years. FL shows an inherent advantage privacy preservation, since users' raw data are processed locally. However, it relies on centralized server to perform model aggregation. Therefore, is vulnerable malfunctions and external attacks. In this paper, we propose novel framework by integrating blockchain into FL, namely, assisted decentralized federated (BLADE-FL), enhance the security FL....
Genome-wide association studies (GWASs) have been widely applied in the neuroimaging field to discover genetic variants associated with brain-related traits. So far, almost all GWASs conducted genetics are performed on univariate quantitative features summarized from brain images. On other hand, powerful deep learning technologies dramatically improved our ability classify In this study, we proposed and implemented a novel machine strategy for systematically identifying that lead detectable...
In decentralized federated learning (DFL), clients exchange their models with each other for global aggregation. Due to a lack of centralized supervision, client may easily duplicate shared save its computing resources. Generally, this plagiarism behavior is hard detect, while it harmful model training performance. To address issue, we propose an anti-plagiarism DFL framework efficiently detect misconduct. Specifically, first design method detecting by adding time-shift pseudo-noise (PN)...
Conventional synchronous federated learning (SFL) frameworks suffer from performance degradation in heterogeneous systems due to imbalanced local data size and diverse computing power on the client side. To address this problem, asynchronous FL (AFL) semi-asynchronous have been proposed recover loss by allowing aggregation. However, aggregation incurs a new problem of inconsistency between updates global updates. Motivated issues conventional SFL AFL, we first propose time-driven (T-SFL)...
Digital twin (DT) has emerged as a promising solution to enhance manufacturing efficiency in industrial Internet of Things (IIoT) networks. To promote the and trustworthiness DT for wireless IIoT networks, we propose blockchain-enabled (B-DT) framework that employs deep neural network (DNN) partitioning technique reputation-based consensus mechanism, wherein DTs maintained at gateway side execute DNN inference tasks using data collected from their associated devices. First, employ offload...
Genome-wide association studies (GWASs) have been widely applied in the neuroimaging field to discover genetic variants associated with brain-related traits. So far, almost all GWASs conducted genetics are performed on univariate quantitative features summarized from brain images. On other hand, powerful deep learning technologies dramatically improved our ability classify In this study, we proposed and implemented a novel machine strategy for systematically identifying that lead detectable...