Sarah Erfani

Papers

Total Citations

H-Index

About

Sarah Erfani is a leading researcher at the intersection of quantum computing, machine learning, and artificial intelligence safety. Her work primarily focuses on adversarial robustness—understanding and defending against malicious inputs that can fool neural networks—and on improving the efficiency of multiagent reinforcement learning systems. Her most impactful contribution is the landmark study "Benchmarking Adversarially Robust Quantum Machine Learning at Scale" (2023, 59 citations), which provides the first large-scale empirical evaluation of how quantum machine learning models withstand adversarial attacks, establishing critical baselines for the field. In parallel, her 2025 paper "Algorithmically-designed reward shaping for multiagent reinforcement learning in navigation" (3 citations) introduces a novel automated approach to reward design that dramatically reduces the manual effort required for training cooperative AI agents. Erfani’s work bridges fundamental theory and practical deployment, offering both rigorous benchmarks and scalable solutions. Her research is essential reading for anyone working on trustworthy AI, quantum-enhanced learning, or multiagent systems, and her citation record reflects her growing influence in shaping the next generation of robust, efficient machine learning.