Christopher Leckie

Papers

Total Citations

H-Index

About

Christopher Leckie is a leading researcher at the intersection of quantum computing and machine learning, with a primary focus on adversarial robustness and scalable benchmarking. His major contributions center on systematically evaluating the vulnerability of quantum machine learning (QML) models to adversarial attacks—a critical challenge as neural networks become ubiquitous across science and industry. Leckie’s landmark work, "Benchmarking Adversarially Robust Quantum Machine Learning at Scale" (2023, 59 citations), established rigorous frameworks for testing how quantum classifiers withstand carefully crafted malicious inputs, revealing both strengths and weaknesses compared to classical counterparts. This research has profound implications for deploying QML in security-sensitive applications, from autonomous systems to financial modeling. Beyond his citation impact, Leckie is recognized for bridging theoretical robustness guarantees with practical, large-scale experiments, setting new standards for reproducible evaluation in the field. His work not only advances foundational understanding of quantum adversarial examples but also provides essential tools for developing next-generation, trustworthy AI systems. Leckie continues to shape the dialogue on how quantum advantages can be realized without compromising security.