4 papers
Taipan: A Query-free Transfer-based Multiple Sensitive Attribute Inference Attack Solely from Publicly Released Graphs
Ying Song, Balaji Palanisamy
Graph-structured data underpin a wide spectrum of modern applications. However, complex graph topologies and homophilic patterns can facilitate attribute inference attacks (AIAs) b…
GraphToxin: Reconstructing Full Unlearned Graphs from Graph Unlearning
Ying Song, Balaji Palanisamy
Graph unlearning 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,…
Krait: A Backdoor Attack Against Graph Prompt Tuning
Ying Song, Rita Singh, Balaji Palanisamy
Graph prompt tuning has emerged as a promising paradigm to effectively transfer general graph knowledge from pre-trained models to various downstream tasks, particularly in few-sho…
MAPPING: Debiasing Graph Neural Networks for Fair Node Classification with Limited Sensitive Information Leakage
Ying Song, Balaji Palanisamy
Despite remarkable success in diverse web-based applications, Graph Neural Networks(GNNs) inherit and further exacerbate historical discrimination and social stereotypes, which cri…