Bio

Alexander Robey is a postdoctoral researcher in the Machine Learning Department at Carnegie Mellon University, where he is advised by J. Zico Kolter. He is also affiliated with Gray Swan, a start-up developing AI models resistant to adversarial attacks.

In August 2024, he received his Ph.D. from the Department of Electrical and Systems Engineering at the University of Pennsylvania, advised by Hamed Hassani and George J. Pappas. His dissertation, titled Algorithms for Adversarially Robust Deep Learning, was awarded the 2024 Charles Hallac and Sarah Keil Wolf Award for Best Dissertation in the department. While at Penn, he was a member of the ASSET Center for Safe, Explainable and Trustworthy Machine Learning, the Warren Center for Network and Data Sciences, and the GRASP Robotics Laboratory. He previously served as a Visiting Instructor in the Department of Engineering at Swarthmore College (2024), a research intern at Google Cloud AI (2022-23), and a computational intern at Lawrence Livermore National Laboratory (2017). He received a B.A. in Mathematics and a B.S. in Engineering from Swarthmore College in 2018.

Alexander Robey was named a Rising Star in Adversarial Machine Learning at the NeurIPS 2024 Workshop on Frontiers in Adversarial Machine Learning and a Rising Star in Cyber-Physical Systems by the National Science Foundation. He has received Best Paper Awards for Adversarial Training Should Be Cast as a Non-Zero-Sum Game at the ICML 2023 Workshop on Frontiers in Adversarial Machine Learning and for Jailbreaking LLM-Controlled Robots at the Princeton Symposium on Safe Deployment of Foundation Models in Robotics. In 2023, he was awarded a fellowship from Amazon to support research on fair and trustworthy AI. He also received the Dean's Fellowship from the University of Pennsylvania in 2018 and the Undergraduate Research Fellowship from Swarthmore College in 2016. His work has been covered by WIRED, MIT Technology Review, IEEE Spectrum, and The Washington Post.