BEN EDELMAN
Ben Edelman is a computer scientist and AI researcher. In his research, he has built foundational scientific understanding of learning dynamics in AI models and explored the interplay between machine learning and strategic incentives. His work has been awarded spotlight status at major deep learning conferences, featured on the blogs of OpenAI and Anthropic, and covered by The Economist and The Brookings Institution. He holds a Ph.D. in Computer Science from Harvard University and an undergraduate degree in Mathematics from Princeton University.
Ben is serving as the Agent Security Lead for the Center for AI Standards and Innovation. His team tracks the vulnerability of AI systems to adversarial attacks, and advances the secure development, deployment, and use of AI.