A realistic model extraction attack against graph neural networks

F Guan, T Zhu, H Tong, W Zhou - Knowledge-Based Systems, 2024 - Elsevier
Abstract Model extraction attacks are considered to be a significant avenue of vulnerability in
machine learning. In model extraction attacks, the attacker repeatedly queries a victim model …

VidModEx: Interpretable and Efficient Black Box Model Extraction for High-Dimensional Spaces

SS Kumar, Y Govindarajulu, P Kulkarni… - arxiv preprint arxiv …, 2024 - arxiv.org
In the domain of black-box model extraction, conventional methods reliant on soft labels or
surrogate datasets struggle with scaling to high-dimensional input spaces and managing the …