Safety in Graph Machine Learning: Threats and Safeguards

TL;DR

This survey reviews safety challenges in Graph Machine Learning, categorizing threats to reliability, generalizability, and confidentiality, and discusses strategies to develop safer, more trustworthy Graph ML models for high-stakes applications.

Contribution

It introduces a novel taxonomy of threats and provides a systematic review of safety strategies in Graph ML, guiding future research in safety-centered model development.

Findings

Threats are categorized into model, data, and attack threats.

Effective safety strategies are identified for each threat category.

The review emphasizes the importance of safety practices in high-stakes domains.

Abstract

Graph Machine Learning (Graph ML) has witnessed substantial advancements in recent years. With their remarkable ability to process graph-structured data, Graph ML techniques have been extensively utilized across diverse applications, including critical domains like finance, healthcare, and transportation. Despite their societal benefits, recent research highlights significant safety concerns associated with the widespread use of Graph ML models. Lacking safety-focused designs, these models can produce unreliable predictions, demonstrate poor generalizability, and compromise data confidentiality. In high-stakes scenarios such as financial fraud detection, these vulnerabilities could jeopardize both individuals and society at large. Therefore, it is imperative to prioritize the development of safety-oriented Graph ML models to mitigate these risks and enhance public confidence in their applications. In this survey paper, we explore three critical aspects vital for enhancing safety in Graph ML: reliability, generalizability, and confidentiality. We categorize and analyze threats to each aspect under three headings: model threats, data threats, and attack threats. This novel taxonomy guides our review of effective strategies to protect against these threats. Our systematic review lays a groundwork for future research aimed at developing practical, safety-centered Graph ML models. Furthermore, we highlight the significance of safe Graph ML practices and suggest promising avenues for further investigation in this crucial area.