ফেডারেটেড লার্নিং — হাসপাতালের জন্য উন্নত নির্দেশিকা
From FedAvg and FedOpt to gradient-leakage defense, differential privacy, Secure Aggregation, blockchain FL, homomorphic encryption, post-quantum cryptography, and model compression.
Exploring federated learning, AI security, privacy, blockchain, and cryptography — written for developers, researchers, and curious minds.
Featured Post
A comprehensive guide covering FedAvg → FedOpt, gradient leakage attacks, differential privacy, Secure Aggregation, blockchain FL, homomorphic encryption, post-quantum crypto, model compression, and more.
Dive deeper into federated learning, privacy-preserving AI, blockchain, and cryptography.
From FedAvg and FedOpt to gradient-leakage defense, differential privacy, Secure Aggregation, blockchain FL, homomorphic encryption, post-quantum cryptography, and model compression.
Hands-on explanations, diagrams, simulators, and real-world security analysis of privacy-preserving machine learning.
FedAvg, FedProx, SCAFFOLD, FedOpt, FedNova — and how client selection shapes accuracy.
Gradient leakage, membership inference, poisoning, backdoors, DP-SGD, Secure Aggregation.
Smart-contract coordination, incentive mechanisms, and scalability trade-offs.
AES, RSA/ECDH, Homomorphic Encryption, SMPC, ZKP, and post-quantum migration.
About Me
Computer Science & Engineering undergraduate at Southeast University and an aspiring AI/ML engineer. I build intelligent systems with deep learning, and I write this blog to share what I learn about federated learning, AI security, privacy, blockchain, and cryptography — explained with real code, diagrams, and hands-on experiments.