ROVER: Robust Generative Continual Identity Unlearning Against Relearning Attacks

Tairan Huang; Qiang Chen; Beibei Hu; Yunlong Zhao; Hongyan Xu; Zhiyuan Chen; Yi Chen; Xiu Su

AAAI 2026technical0 citations

ROVER: Robust Generative Continual Identity Unlearning Against Relearning Attacks

Tairan Huang, Qiang Chen, Beibei Hu, Yunlong Zhao, Hongyan Xu, Zhiyuan Chen, Yi Chen, Xiu Su

Abstract

Recent generative unlearning models synthesize high quality samples while protecting private information by unlearning the identity. However, existing generative identity unlearning methods face two challenges in multi-identity unlearning: 1) identity conflicts, which cause conflicts of model parameters in the continuous erasure of multiple identities; 2) fragile unlearning, where the model

BibTeX

@inproceedings{aaai2026_roverrobustgener,
  title = {ROVER: Robust Generative Continual Identity Unlearning Against Relearning Attacks},
  author = {Tairan Huang and Qiang Chen and Beibei Hu and Yunlong Zhao and Hongyan Xu and Zhiyuan Chen and Yi Chen and Xiu Su},
  booktitle = {AAAI 2026},
  year = {2026}
}