Synthetic Dataset for Blockchain Federated learning

The proposed model intentionally uses a synthetic federated dataset to simulate a decentralized environment, controlled non-IID distributions, adversarial clients, and privacy constraints. These are difficult to obtain from real hospital collaborations due to ethical limitations and strict sharing regulations.

A synthetic federated classification dataset used for processing Enhanced Blockchain Federated Learning framework with FedAdam, differential privacy, secure aggregation, attention-based trust weighting, and blockchain verification. The decentralized environment is offered by synthetic dataset where clients possess private, heterogeneous, and non-IID local data. In view of privacy, security, and regulatory constraints, the aspects processed such as IoT nodes, financial branches, or edge device than centralized processing. The dataset describes 12K samples distributed to 20 clients, in which 600 local items per client. The 13 attributes in which 12 are numerical and 1 binary present in each sample where binary label denotes normal and abnormal. The class setup in dataset resembles 60% of majority class and 40% of minority class distributions. A non-IID atmosphere is created to emulate heterogeneity in terms of diverse features, and noise levels. In this, trust resistance is tested on low trust clients who generate noisy or adversarial updates. The raw details are client, allows only model updates to be shared, provides decentralized aggregation, privacy preserving, and accuracy.

For experimental setup, the dataset is split into Training set as 70%, Validation set as 15%, and 15% for Test set. Then applies preprocessing before local training, then local training, then applies ingegrated set of methods for ensuring privacy and security, and compares performance of derived model against other existing models such as FedAvg, FedProx, Krum Aggregation, Median Aggregation, Basic BFL, BFL + Secure Aggregation + DP,  BFL with Adaptive Trust + Secure Aggregation + DP, BFL with FedProx + Trust + DP + Secure Aggregation, and Enhanced BFL with FedAdam + Attention + Trust + DP + Blockchain. The dataset defines columns such as Sample_ID as unique sample identifier, Client_ID as federated client node, normalized numerical features as F1–F12 which are Transaction_Amount, Transaction_Frequency, Account_Balance, Device_Trust_Level, Login_Frequency, Location_Risk_Score, IP_Reputation_Score, Session_Duration,, Failed_Login_Attempts, Historical_Trust_Index, Behavioral_Deviation_Score, and Data_Integrity_Score, Class_Label as binary class (0/1) that denotes normal or abnormal, Client_Type as Reliable / Low_Trust / Malicious, Trust_Score as initial adaptive trust score, and Anomaly_Flag denotes whether the client behavior is suspicious.