REVIEW 6 cited by
Safety in Graph Machine Learning: Threats and Safeguards
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original 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.
Forward citations
Cited by 6 Pith papers
-
Federated Graph Learning with Graphless Clients
FedGLS trains federated graph models when some clients have only node features and no graph edges, by distilling structure knowledge into a feature encoder and generating graphs locally on graphless clients.
-
Generative Risk Minimization for Out-of-Distribution Generalization on Graphs
GRM replaces discrete subgraph extraction with a continuous generative model and reports state-of-the-art results on graph out-of-distribution benchmarks.
-
Virtual Nodes Can Help: Tackling Distribution Shifts in Federated Graph Learning
FedVN learns shared virtual nodes and client-specific edge generators so the global GNN is trained on augmented graphs that are more similar across clients.
-
Toward Scalable Graph Unlearning: A Node Influence Maximization based Approach
The paper's NIM+SGU pipeline improves forgetting and preserves accuracy in graph unlearning by selecting high-influence nodes via propagation-based influence scores and fine-tuning on entity-specific losses.
-
Enhancing Distribution and Label Consistency for Graph Out-of-Distribution Generalization
DLG unifies augmented and invariant graph generation via edge masks and adds distribution and label consistency losses, reporting improved OOD accuracy on graph benchmarks.
-
A Systematic Survey of Model Extraction Attacks and Defenses: State-of-the-Art and Perspectives
The paper classifies model extraction attacks and defenses into attack, defense, and computing environment categories and surveys their current state.
Discussion (0). Continue with ORCID to comment.