SAGNN+CS: A Resilient Graph Neural Network Framework Against Backdoor Threats
Bibliographic record
Abstract
Graph neural networks (GNNs) have become indispensable in high-stakes domains such as healthcare and finance, yet their vulnerability to adversarial backdoor attacks presents critical security risks. These attacks can manipulate GNNs to produce targeted misclassifications by injecting malicious triggers during training, compromising model reliability in production environments. While traditional GNN architectures rely on explicit defense mechanisms against such threats, developing inherently robust architectures remains an open challenge. In this work, we leverage the enhanced expressiveness of higher-order GNNs to propose a novel architecture incorporating a cosine similarity-based subgraph extraction policy. Our approach prioritizes semantically similar neighbors during message passing, enabling better capture of local graph structure while strengthening resilience against out-of-distribution triggers. Through extensive experiments across multiple datasets and attack scenarios, we demonstrate that our method significantly reduces backdoor attack success rates compared to state-of-the-art baselines. These results establish a promising direction for developing inherently robust GNN architectures suitable for deployment in security-critical applications. Keywords: GNNs, Backdoor attacks, Robustness, Security.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".