The Center for Education and Research in Information Assurance and Security (CERIAS)

The Center for Education and Research in
Information Assurance and Security (CERIAS)
Center for Education and Research in Information Assurance and Security

Machine Unlearning

Research Areas: Artificial Intelligence and Machine Learning

Principal Investigator: Rajiv Khanna

We analyze unlearning when a model must forget a designated subset while retaining utility on the rest, characterizing howsharpness‑oriented loss landscape via optimization interacts with forget/retain signals and when it helps or hurts—providing theory‑guided trade‑offs and diagnostics.