Reshmi Mitra

Revamping Federated Learning Security from a Defender's Perspective: A Unified Defense with Homomorphic Encrypted Data Space

2024

Federated Learning (FL) facilitates clients to collaborate on training a shared machine learning model without exposing individual private data. Nonetheless, FL remains susceptible to utility and privacy attacks, notably evasion data poisoning and model inversion …

Securing Inverter-Based Resources via Knowledge-Driven Threat Modeling, Analysis, and Mitigation

2025

Inverter-based Resources (IBRs) present unique cybersecurity challenges due to their digital control systems and connection to the electric grid. They rely on digital communications and control systems, making them vulnerable to cyberattacks. These attacks can …