GraphToxin: Reconstructing Full Unlearned Graphs from Graph Unlearning

Excerpt

arXiv:2511.10936v3 Announce Type: replace Abstract: Graph unlearning (GU) has emerged as a promising solution to comply with "the right to be forgotten" regulations by enabling the removal of sensitive information upon request. However, this solution is not foolproof. The involvement of multiple parties creates new attack surfaces, and residual traces of deleted data can persist within the unlearned graph neural networks (GNNs). These vulnerabilities can be exploited by attackers to recover the