Bhavya Kailkhura is a research scientist at Lawrence Livermore National Laboratory (LLNL), specializing in safe and trustworthy artificial intelligence (AI). He earned his M.S. and Ph.D. in Electrical Engineering from Syracuse University (2012, 2016) and joined LLNL as a postdoctoral researcher in 2016. He currently leads initiatives focused on advancing AI for scientific applications and ensuring the development of safe, secure AI systems. He also serves on the council of LLNL’s Data Science Institute. His research interests include large language models (LLMs) for scientific applications, AI safety and alignment, adversarial robustness, and uncertainty quantification. He has a strong track record of innovation in reliable machine learning and has led multiple federally funded projects to enhance the robustness and security of AI systems.

Syracuse University, PH.D. IN ELECTRICAL AND COMPUTER ENGINEERING (2012 - 2016), Thesis: Distributed Inference and Learning with Adversarial Data

Books

[1] A. Vempaty, B. Kailkhura, and P. K. Varshney, "Secure Networked Inference with Unreliable Data Sources", Springer Nature, 2018.

Journal/Conference Papers

See Google Scholar for a complete list.

• LLNL Early and Mid-Career Recognition (EMCR) Award, 2024
• Director’s Science and Technology Excellence in Publication Award (2019, 2024), LLNL
• IEEE Senior member, 2023
• Best Paper Award: ICLR 2022 Workshop on Socially Responsible Machine Learning (SRML), AAAI 2025 Workshop on Connecting Low-Rank Representations in AI (CoLoRAI)
• All University Doctoral Prize for outstanding Ph.D. dissertation, Syracuse University, 2016