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

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

26 May 2024arXiv:2405.16405archive 2025-07-28

Runlin Lei, Yuwei Hu, Yuchen Ren, Zhewei Wei

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.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 24 code samples harvested from 1 repository linked to this paper: 17 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 9 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 24 samples from 1 repository, 17 ran (8 with no instrument failure; 9 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 17 samples that ran has no recorded date.

leirunlin/text-level-graph-attack officialmentioned in papermentioned on GitHubpytorchSyntology: 24 samples, 17 ran (9 instrument-failed) · 7 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

24 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 9 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
7ran · our draft was wrong
2ran; the contract check could not run
7ran
7unverified

Licence: 24 of the 24 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from leirunlin/text-level-graph-attack. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

leirunlin/text-level-graph-attack official repository 24 samples, 17 ran (9 instrument-failed) · 7 unverified
GCNAdjNorm models/model_pyg.py ran · our draft was wrong no licence file found · pointer only · 031697fa4856f0d8 · report fixture: signature adj:csr_matrix/2/float, order:float/0/float · returned csr_matrix · level recorded 2026-09-24
api_endpoint_from_url in 10 papers async_api.py ran · our draft was wrong no licence file found · pointer only · 0a0bc4ba8c9af478 · report fixture: signature request_url:str/0/str · returned str · level recorded 2026-09-22
edge_sim_analysis attacks/attack.py ran; the contract check could not run (RAISES) no licence file found · pointer only · ee46ccc0db279d01 · report fixture: signature edge_index:Tensor/2/int, features:Tensor/2/float · returned ndarray · level recorded 2026-09-24
edge_sim_estimate attacks/attack.py ran no licence file found · pointer only · 15b4190a079900a4 · report fixture: signature x:Tensor/2/float, adj:SimpleAdj/0/?, num:int/0/int, style:str/0/str · returned Tensor · level recorded 2026-09-24
feat_normalize utils.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 5a4d75b2856d14b5 · report fixture: signature features:Tensor/2/float, norm:str/0/str, lim_min:float/0/float, lim_max:float/0/float · returned Tensor · level recorded 2026-09-25
generate_grb_split load_graph.py ran no licence file found · pointer only · e1d1786f30e5fe91 · report fixture: signature data:MinimalData/0/?, mode:str/0/str · returned tuple · level recorded 2026-09-24
generate_percent_split load_graph.py ran no licence file found · pointer only · cc6b381c885cee8d · report fixture: signature dataset:MockDataset/0/?, seed:int/0/int, train_percent:int/0/int, val_percent:int/0/int · returned tuple · level recorded 2026-09-24
generate_split in 9 papers load_graph.py ran no licence file found · pointer only · 9ed828c70754da92 · report fixture: signature dataset:MockDataset/0/?, seed:int/0/int, train_num_per_c:int/0/int, val_num_per_c:int/0/int · returned tuple · level recorded 2026-09-24
get_tf_idf_by_texts attacks/text_utils.py ran · honoured contract no licence file found · pointer only · 9881692295f797a9 · report fixture: signature texts:list/1/str, max_features:int/0/int, use_tokenizer:bool/0/bool · returned tuple · level recorded, date not recorded
persist_cache_to_disk api.py ran · our draft was wrong no licence file found · pointer only · f4cc3f30e8c88187 · report fixture: signature filename:str/0/str · returned function · level recorded 2026-09-24
prompt_zero_shot ego_graph.py ran no licence file found · pointer only · 98699449238cacb8 · report fixture: signature data_obj:MockDataObj/0/?, sampled_test_node_idxs:list/1/int, train_node_idxs:list/1/int, topk:bool/0/bool, need_class:bool/0/bool, instruction_format:str/0/str, mapping:dict/0/?, all_possible:bool/0/bool, cot:bool/0/bool, memory_limit:int/0/int · returned tuple · level recorded 2026-09-24
random_string in 8 papers LLM_utils.py ran · our draft was wrong fingerprinted no licence file found · pointer only · ac99c179b0418ee8 · report fixture: signature length:int/0/int · returned str · level recorded 2026-09-24
read_jsonl in 136 papers LLM_utils.py ran · our draft was wrong no licence file found · pointer only · f6dadc26879ae08a · report fixture: signature file_path:str/0/str · returned list · level recorded 2026-09-24
sep_test gnn_misg.py ran no licence file found · pointer only · 38d1baa3ab10748b · report fixture: signature model:callable/0/?, x:Tensor/2/float, adj_t:Tensor/2/float, y:Tensor/2/int, target_idx:Tensor/1/int, evaluator:MinimalEvaluator/0/? · returned float · level recorded 2026-09-24
target_select utils.py ran no licence file found · pointer only · 231f26eaddf19604 · report fixture: signature model:callable/0/?, adj:Tensor/2/float, features:Tensor/2/float, labels:Tensor/1/int, target_idx:Tensor/1/int, num:int/0/int · returned Tensor · level recorded 2026-09-24
test in 377 papers gnn_misg.py ran · our draft was wrong no licence file found · pointer only · 768b8716889709e2 · report fixture: signature model:callable/0/?, x:Tensor/2/float, adj_t:Tensor/2/float, y:Tensor/2/int, split_idx:dict/0/?, evaluator:Evaluator/0/? · returned tuple · level recorded 2026-09-22
train in 522 papers gnn_misg.py ran · our draft was wrong no licence file found · pointer only · 15cbb9f3adf7eca7 · report fixture: signature model:callable/0/?, x:Tensor/2/float, adj_t:Tensor/2/float, y:Tensor/1/int, train_idx:Tensor/1/int, optimizer:Adam/0/? · returned float · level recorded 2026-09-22
get_bow_by_texts attacks/text_utils.py unverified no licence file found · pointer only · 5d5bd3804f348b08 · report
get_bow_by_texts data_preprocess.py unverified no licence file found · pointer only · 96e4fd4bc45d23ce · report
get_embedding in 28 papers api.py unverified no licence file found · pointer only · ccb546755da4914b · report
get_tf_idf_by_texts data_preprocess.py unverified no licence file found · pointer only · d38549dfb19c8a66 · report
load_vectorizer attacks/text_utils.py unverified no licence file found · pointer only · 2889448e99db8045 · report
load_yaml_file in 9 papers api.py unverified no licence file found · pointer only · 2c594a3c725da903 · report
num_tokens_consumed_from_request in 10 papers async_api.py unverified no licence file found · pointer only · 27007d0ec4adb00b · report

Tasks

Language ModellingLarge Language Model

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections