What type of study is this?

This is a Quantitative Study study (also classified as: Experimental Study).

September 30, 2025Open Access

An Out-Of-Distribution Membership Inference Attack Approach for Cross-Domain Graph Attacks

View Full Paper

Ask AI

Bookmark

Authors

Novel approach introduces an OOD framework for membership inference attack in cross-domain graph scenarios, improving attack adaptability.

GOOD-MIA shows superior performance in membership inference attacks across diverse domains, enhancing data privacy.
Examined topological structures reveal critical insights into node representations, improving attack effectiveness.
The method constructs shadow subgraphs capturing distribution diversity, addressing significant limitations in traditional assumptions.
Optimizing domain adaptability during inference broadens the attack's applicability, making it relevant for various datasets.

Wang et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

Novel approach introduces an OOD framework for membership inference attack in cross-domain graph scenarios, improving attack adaptability.