Selective Fine-Tuning for Targeted and Robust Concept Unlearning

Mansi, Avinash Kori, Francesca Toni, Soteris Demetriou
November 2026
Preprint PDF Cite Project DOI
Type
Conference paper
Publication
Proceedings of the 33rd ACM SIGSAC Conference on Computer and Communications Security (CCS)
Machine Unlearning Fine-Tuning Concept Removal Large Language Models AI Safety Diffusion Models

Related