Tingwei Zhang is a PhD candidate in Computer Science at Cornell Tech, advised by Vitaly Shmatikov. He received his undergraduate degree in Computer Science from the University of Virginia. His research focuses on the security and privacy of AI systems, particularly understanding how adversarial manipulation can shape the behavior and outputs of modern AI systems and developing methods to make them more robust. His work spans multimodal models, retrieval systems, and AI agents. As a DLI Fellow, he explores how adversarial manipulation of AI systems can affect information integrity, accountability, and public trust as these systems increasingly mediate how people access and interpret information.