WPI Researchers Receive NSF CAREER Awards

Ganji’s CAREER project will focus on privacy-preserving neural networks (PPNN), a type of AI that is designed to function on AI chips without revealing sensitive data to unauthorized parties. She will develop approaches to thwart three types of attacks: backdoor attacks that insert malicious functionality into AI chips; side-channel attacks that leverage inevitable information leakage, such as power consumption, to infer private information; and fault-injection attacks that physically alter hardware to extract data.

“AI accelerators are in devices everywhere, from home security cameras to hospital treatment rooms,” Ganji said. “Privacy-preserving accelerators on those devices have been considered secure and private, but research at WPI has uncovered potential vulnerabilities that should be explored and addressed so that users can be assured of privacy.”

Ganji joined the WPI faculty in 2020. She earned her PhD from the Technical University of Berlin and was a postdoctoral associate at the Telecom Innovation Laboratories/Technical University of Berlin and the University of Florida. Her research focuses on interdisciplinary approaches to machine learning and cryptography for the design and evaluation of security-critical hardware.

Che’s CAREER project will focus on developing an AI-enabled, multiscale simulation framework that will help explain how self-assembled organic compounds attached to metals can speed up and improve carbon capture and electrochemical conversion processes. The research will establish predictive design principles linking molecular-scale interactions to catalytic performance and create new AI-enabled tools for accelerating catalyst discovery, reaction optimization, and scientific understanding of complex chemical systems.

“The overarching goal of this research is to develop a physics-integrated and interpretable AI framework that can predict how molecular interfaces control carbon capture and conversion reactions,” Che said. “Simulations, when validated by real-world experiments, can help researchers find the materials and processes that will accelerate catalyst discovery and reaction optimization.”

Che, who joined the WPI faculty in 2025, focuses her research on using AI to guide the design of energy-saving catalysts and catalytic technologies. She received her PhD at Washington State University and did postdoctoral research at the University of Toronto and the University of Delaware. 

Both Ganji and Che will integrate new opportunities for student learning into their projects. Ganji will participate in WPI programs aimed at students in grades 9–11, work with undergraduates to perform and publish research, and advise undergraduate teams working on capstone projects that all WPI undergraduates undertake as part of their degrees. Che will develop hands-on demonstrations for K–12 students, launch a new graduate-level course on applied machine learning in engineering, and bring lectures on computational electrocatalysis and machine learning to her YouTube channel.