Conducted a comprehensive survey on Quantum Federated Learning (QFL), analyzing its architecture, limitations, and integration strategies.
Explored quantum security techniques, such as quantum key distribution and GHZ state entanglement, to enhance privacy in federated learning.
Investigated hybrid quantum-classical approaches to optimize scalability, efficiency, and security in decentralized networks.
Identified potential advancements in QFL to address challenges in privacy, scalability, and computational efficiency.
Proposes a novel CircUit-Level backdoor Threat (CULT) model that formalizes four stealthy attacks by exploiting quantum-aware mechanisms, including Grover, Pauli, Bit-flip, and Sign-flip
Experiments on the MNIST and CIFAR-10 datasets with non-IID splits and varying fractions of malicious clients show that even a single malicious client can induce severe accuracy degradation under FedAvg aggregation
Popular defenses, including Krum, Multi-Krum, FoolsGold, FLGuardian, and Mud-HoG, reduce degradation in many regimes, but they fail to eliminate worst-case failure cases, where accuracy drops up to 50\%.
SLID: Scalable Lightweight Intrusion Detector
Focused on attack identification and mitigation in resource-constrained IoT devices.
Crossed State-Of-The-Art accuracies with a lighter model and optimized feature selection technique.
Proposes a hybrid CNN-LSTM model with 99.9% score for : Accuracy, Precision, Recall, and F1-score.