Deepa Kundur
3 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
This paper evaluates the vulnerability of leading LLMs deployed in smart grid operations to jailbreaking attacks, finding that while some models show high susceptibility, Claude 3.5 Haiku demonstrated complete resistance.
The paper proposes an AI-based supervisory layer using a recurrent neural network to validate the physical integrity of current measurements used by line current differential relays in inverter-based microgrids, thereby defending against false-data injection attacks.
This paper demonstrates that an off-the-shelf Large Language Model (LLM) can function as a high-performing, explainable, human-in-the-loop layer for detecting cyberattacks in Industrial Control System (ICS) Modbus traffic.
Papers
Large Language Models as Explainable Cyberattack Detectors for Energy Industrial Control Systems
This paper demonstrates that an off-the-shelf Large Language Model (LLM) can function as a high-performing, explainable, human-in-the-loop layer for detecting cyberattacks in Industrial Control System…