Private Graph Extraction via Feature Explanations

Abstract

Privacy and interpretability are two important ingredients for achieving trustworthy machine learning. We study the interplay of these two aspects in graph machine learning through graph reconstruction attacks. The goal of the adversary here is to reconstruct the graph structure of the training data given access to model explanations. Based on the different kinds of auxiliary information available to the adversary, we propose several graph reconstruction attacks. We show that additional knowledge of post-hoc feature explanations substantially increases the success rate of these attacks. Further, we investigate in detail the differences between attack performance with respect to three different classes of explanation methods for graph neural networks: gradient-based, perturbation-based, and surrogate model-based methods. While gradient-based explanations reveal the most in terms of the graph structure, we find that these explanations do not always score high in utility. For the other two classes of explanations, privacy leakage increases with an increase in explanation utility. Finally, we propose a defense based on a randomized response mechanism for releasing the explanations, which substantially reduces the attack success rate. Our code is available at https://github.com/iyempissy/graph-stealing-attacks-with-explanation

arXiv commentAccepted at PETS 2023

References in corpus (10)

• Efficient Estimation of Word Representations in Vector Space
• Axiomatic Attribution for Deep Networks
• European Union regulations on algorithmic decision-making and a "right to explanation"
• Adversarial Attacks on Graph Neural Networks via Meta Learning
• Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future
• Learning Discrete Structures for Graph Neural Networks
• GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks
• Stealing Links from Graph Neural Networks
• Model Extraction Attacks on Graph Neural Networks: Taxonomy and Realization
• LinkTeller: Recovering Private Edges from Graph Neural Networks via Influence Analysis