Aravind Cheruvu
Aravind Cheruvu is a Ph.D. student in the Department of Computer Science. His advisor is Danfeng (Daphne) Yao.
Cheruvu’s research focuses on generative AI safety, adversarial security, and agentic cybersecurity. He builds responsible AI frameworks to defend against adaptive attacks across both textual and visual domains.
Currently, Aravind is working on self-investigating LLM agents for automated security operations. His research enables autonomous agents to bridge the gap between detection and investigation, which allows for more efficient analysis of complex security threats.