M. E. Sevior

Papers

Total Citations

H-Index

About

M. E. Sevior is a leading researcher at the intersection of quantum computing and machine learning, with a primary focus on adversarial robustness. Their most impactful work, "Benchmarking adversarially robust quantum machine learning at scale" (2023), has already garnered 59 citations, establishing a critical foundation for understanding how quantum neural networks can be defended against malicious inputs. This research addresses a fundamental vulnerability in modern AI: while classical neural networks are easily fooled by carefully crafted adversarial attacks, Sevior's work systematically benchmarks quantum ML models to determine if they offer inherent advantages in robustness. By scaling these benchmarks, they provide the first comprehensive framework for evaluating security in quantum machine learning systems. Their contributions are particularly timely as quantum computing moves from theoretical promise to practical implementation, and their findings have direct implications for developing secure AI systems in sensitive applications. Sevior's work bridges two rapidly evolving fields, offering both theoretical insights and practical methodologies that will shape how future quantum-classical hybrid systems are designed and deployed.