I am a Ph.D. student in AI and Security, specializing in privacy-preserving machine learning, federated learning, and adversarial robustness in decentralized AI systems. My research focuses on developing secure AI architectures, integrating blockchain-based privacy mechanisms, zero-knowledge proofs, and federated learning, while recently expanding into the security of Spiking Neural Networks (SNNs).

• Privacy-Preserving AI – Developing secure and scalable machine learning frameworks using federated learning, differential privacy, and cryptographic techniques.
• Decentralized AI & Blockchain – Exploring blockchain-based security models and distributed trust mechanisms for AI governance.
• Adversarial Robustness – Investigating defenses against model inversion, backdoor attacks, and inference risks.

• Secure Cyber Threat Intelligence Sharing (SeCTIS) – A blockchain & swarm learning framework for privacy-preserving CTI exchange using zero-knowledge proofs.
• Class-Aware Gradient Masking in Federated Learning – A novel method to enhance privacy, improve convergence, and defend against backdoor attacks in non-IID federated settings.
• Secure & Federated Dataset Distillation (SFDD) – Developing privacy-enhanced dataset distillation using Local Differential Privacy (LDPO-RLD) for secure synthetic dataset creation.

• Machine Learning & Deep Learning: PyTorch
• Security & Privacy: Blockchain, Zero-Knowledge Proofs, Differential Privacy
• Federated Learning: FL frameworks, decentralized ML architectures
• Neuromorphic AI: Spiking Neural Networks (SNNs), SnnTorch