Pith. sign in

REVIEW 1 cited by

Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level

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

arxiv 2405.16405 v2 pith:LXMBXOJH submitted 2024-05-26 cs.LG cs.AI

classification cs.LGcs.AI
keywords graphgiastextattacksinjectleveltextualapplications
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Graph Neural Networks (GNNs) excel across various applications but remain vulnerable to adversarial attacks, particularly Graph Injection Attacks (GIAs), which inject malicious nodes into the original graph and pose realistic threats. Text-attributed graphs (TAGs), where nodes are associated with textual features, are crucial due to their prevalence in real-world applications and are commonly used to evaluate these vulnerabilities. However, existing research only focuses on embedding-level GIAs, which inject node embeddings rather than actual textual content, limiting their applicability and simplifying detection. In this paper, we pioneer the exploration of GIAs at the text level, presenting three novel attack designs that inject textual content into the graph. Through theoretical and empirical analysis, we demonstrate that text interpretability, a factor previously overlooked at the embedding level, plays a crucial role in attack strength. Among the designs we investigate, the Word-frequency-based Text-level GIA (WTGIA) is particularly notable for its balance between performance and interpretability. Despite the success of WTGIA, we discover that defenders can easily enhance their defenses with customized text embedding methods or large language model (LLM)--based predictors. These insights underscore the necessity for further research into the potential and practical significance of text-level GIAs.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks

    cs.AI 2025-06 conditional novelty 6.0 of 10

    ATAG-LLM uses LLM-generated text and a similarity proxy to inject nodes that mislead GNN classifiers without touching embeddings.

Pith tools