Avinash Awasthi

Background

About Avinash Awasthi

I’m currently an M.Tech final year student at MNIT Jaipur working on secure, trustworthy, and decentralized AI for next-generation intelligent systems. My research focuses on building robust AI that can operate safely in real-world, adversarial, and large-scale critical infrastructures.I serve as Lead Security & AI Assistant on a DoT-funded project on Secure Decentralized Deep Learning for 6G Communications. Here, I develop Federated Learning, Split Learning, Meta-Learning, and Transformer-based models for secure and efficient communication networks. My work includes adversarially robust intrusion detection systems (IDS), AI-driven anomaly detection, and real-world decentralized testbeds for 6G environments.My work sits at the intersection of AI Security, 6G, and Decentralized Learning, with research recognized at top-tier venues like NDSS 2026 and TrustCom 2025. I focus on adversarial attacks (poisoning, evasion, membership inference), resilient federated learning, explainable AI for IDS, and security for IoAT and future networked ecosystems.Core Areas:• AI Security & Adversarial ML• Federated & Split Learning• Transformers, LLMs, Mamba, Computer Vision• 6G, Digital Twins, Metaverse Communication SystemsI’m passionate about building AI systems that are not just intelligent — but secure, reliable, and deployment-ready.