How Robust Are Higher-Order Graph Neural Networks to Backdoor Attacks?
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Graph neural networks (GNNs) have become integral tools across critical domains like healthcare and finance, yet their widespread adoption has made them attractive targets for adversarial attacks. These malicious attacks can manipulate GNNs into producing incorrect or biased predictions, compromising their reliability in real-world applications. While traditional GNN architectures require explicit defense mechanisms to guard against such threats, higher-order graph neural networks (HOGNNs) have emerged as a promising alternative. Initially developed to address common GNN limitations such as over-smoothing and over-squashing, HOGNNs have demonstrated superior prediction accuracy and expressive power. Our study investigates whether these architectural advantages translate to inherent security benefits. The results reveal that HOGNNs possess intrinsic resistance to backdoor attacks without requiring additional defensive measures, positioning them as robust architectures for deployment in critical applications.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.004 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it