Paper Citation Record · LEDGER

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

As of 8 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 0 inbound Pith citation observations for arXiv:2506.13276.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2506.13276 v1

Coverage vector

measured 24 of 24 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:41:10.219766Z

measured 24 of 24 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

24 of 24 outbound references displayed

verified exact2
verified fuzzy19
unresolved3
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0e20e4f5-da4a-4990-8fb2-de0a1cf1666c · outbound

This paper cites A comprehensive study on text-attributed graphs: Benchmarking and rethinking,.

Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks A comprehensive study on text-attributed graphs: Benchmarking and rethinking,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:41:13.873823Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7a05a54a-819c-4d0a-8106-85a63605ad20 · outbound

This paper cites Adversarial attack on graph structured data,.

Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks Adversarial attack on graph structured data,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:41:13.749821Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d57fc83d-06a2-4188-8a8e-12ed298c08b0 · outbound

This paper cites Adversarial attacks on neural networks for graph data,.

Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks Adversarial attacks on neural networks for graph data,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:41:13.632308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5645341a-76a6-4dc1-88f8-9f9dc3c1d4b1 · outbound

This paper cites TextBugger: Generating Adversarial Text Against Real-world Applications.

Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks TextBugger: Generating Adversarial Text Against Real-world Applications

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:08.262653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bf501f2-0f0b-4484-af94-9014393f58e4 · outbound

This paper cites Petgen: Personalized text generation attack on deep sequence embedding-based classifica- tion models,.

Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks Petgen: Personalized text generation attack on deep sequence embedding-based classifica- tion models,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:41:13.478290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f49748d3-8ca7-4e63-b430-cd8d9d2a44fc · outbound

This paper cites Fasttextdodger: Decision-based adversarial attack against black-box nlp models with extremely high efficiency,.

Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks Fasttextdodger: Decision-based adversarial attack against black-box nlp models with extremely high efficiency,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:41:13.298773Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5c41b451-5b3f-4b42-a7cf-6e2a6df4a9ba · outbound

This paper cites Adversarial attack and defense on graph data: A survey,.

Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks Adversarial attack and defense on graph data: A survey,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:41:13.168352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 211f4f8c-b2a6-47f0-8d8f-77b87ea77643 · outbound

This paper cites Adversarial attacks on node embeddings via graph poisoning,.

Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks Adversarial attacks on node embeddings via graph poisoning,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:41:12.972380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2dd6f12e-2a29-45bc-8e80-263f3cd304a0 · outbound

This paper cites Let graph be the go board: Gradient-free node injection attack for graph neural networks via reinforcement learning,.

Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks Let graph be the go board: Gradient-free node injection attack for graph neural networks via reinforcement learning,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:41:12.818920Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 91013029-705f-407d-8259-716187b624c6 · outbound

This paper cites Tdgia: Effective injection attacks on graph neural networks,.

Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks Tdgia: Effective injection attacks on graph neural networks,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:41:12.588013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 96dd2625-6f31-41d2-b9c1-89d737d244b5 · outbound

This paper cites Understanding and improving graph injection attack by promoting unnoticeability,.

Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks Understanding and improving graph injection attack by promoting unnoticeability,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:41:12.392414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation afb2fc7a-6c3b-4681-8a46-9cddabbbce47 · outbound

This paper cites Adversarial camouflage for node injection attack on graphs,.

Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks Adversarial camouflage for node injection attack on graphs,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:41:12.221144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation bdf03449-b775-468e-97d2-b0652990b4a0 · outbound

This paper cites Single node injection attack against graph neural networks,.

Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks Single node injection attack against graph neural networks,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:41:12.045116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c19b4c95-3e89-402f-a5f0-7344944bd862 · outbound

This paper cites Scalable attack on graph data by injecting vicious nodes,.

Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks Scalable attack on graph data by injecting vicious nodes,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:41:11.870614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9e579968-86a6-4863-b6fe-8e5ecd24bb93 · outbound

This paper cites Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level.

Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:41:10.663043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 95fbeb95-006a-47a3-8a07-a098649d2693 · outbound

This paper cites How does heterophily impact the robustness of graph neural networks?: Theoretical connections and practical implications,.

Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks How does heterophily impact the robustness of graph neural networks?: Theoretical connections and practical implications,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:41:11.701591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9a55e287-8128-42b1-a8b5-16fe17f0140a · outbound

This paper cites Gn- nexplainer: Generating explanations for graph neural networks,.

Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks Gn- nexplainer: Generating explanations for graph neural networks,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:41:11.472373Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ef3cfb4b-e134-48a8-8abe-0d91dd3e4fab · outbound

This paper cites Semi-supervised classification with graph convolutional networks,.

Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks Semi-supervised classification with graph convolutional networks,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:41:11.335873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 18b510a5-2247-4ec4-a322-f979b5df13a0 · outbound

This paper cites Node Injection Attacks on Graphs via Reinforcement Learning.

Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks Node Injection Attacks on Graphs via Reinforcement Learning

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:41:10.478071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ce261ddb-435b-4ee3-8d19-4ddf348cc9f2 · outbound

This paper cites Message injection attack on rumor detection under the black-box evasion setting using large language model,.

Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks Message injection attack on rumor detection under the black-box evasion setting using large language model,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:41:11.157470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a71eed4c-ce8f-4942-8a7f-0a6182c527aa · outbound

This paper cites A survey of graph meets large language model: Progress and future directions,.

Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks A survey of graph meets large language model: Progress and future directions,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:41:10.979981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 77dd4d27-3b43-4a21-9113-62438765568b · outbound

This paper cites Learning on Graphs with Large Language Models(LLMs): A Deep Dive into Model Robustness.

Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks Learning on Graphs with Large Language Models(LLMs): A Deep Dive into Model Robustness

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:10.041480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73933d08-d1c9-4659-8663-5ac2aa331a18 · outbound

This paper cites GraphEdit: Large Language Models for Graph Structure Learning.

Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks GraphEdit: Large Language Models for Graph Structure Learning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:10.129273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4e31686-bd66-4d4e-b815-e4313d59518a · outbound

This paper cites Can large language models improve the adversarial ro- bustness of graph neural networks?.

Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks Can large language models improve the adversarial ro- bustness of graph neural networks?

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:41:10.836355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Pith citing papers

No inbound Pith citation observations are available.