Loading
Life sciences · Preprint
arXiv · September 9, 2026
Posted before peer review. The findings may change or fail to hold.
This is an unrefereed preprint proposing KCES, a training-free computational defense method against adversarial structural attacks on graph neural networks, grounded in graph kernel complexity theory. The work reports extensive computational experiments but has not undergone peer review and lacks validation on real-world or clinical applications; its relevance to practicing clinicians or life-science researchers is not established.
Preprint. Intervention: Kernel-Complexity Edge Sanitization (KCES): a training-free, model-agnostic framework that identifies and prunes high-KC edges using an edge-specific KC score derived from Graph Kernel Complexity and the graph Gram matrix.. Compared with: Representative robust baselines.
KCES consistently outperforms representative robust baselines across diverse attack settings Method scales effectively to large graphs Framework operates as lightweight preprocessing without retraining
Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.
The source did not state who this applies to in practice.
This is an unrefereed arXiv preprint presenting a novel computational method for defending graph neural networks; the work has not undergone peer review and lacks clinical or human validation.
As stated by the source record.
Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.
What is missing. This record has no reported figures. That is a gap in the analysis, not a judgement about the study.
Graph Neural Networks (GNNs) have achieved remarkable success across diverse applications, yet they remain highly vulnerable to adversarial attacks that maliciously perturb graph structure. Existing defenses often lack rigorous theoretical grounding, rely on attack-specific heuristics, or require costly retraining procedures such as adversarial training. To address these limitations, we propose Kernel-Complexity Edge Sanitization (KCES), a training-free and model-agnostic framework for defending against structural attacks. KCES is built upon Graph Kernel Complexity (GKC), a principled metric derived from the graph Gram matrix that appears in a generalization upper bound on the GNN test error. From this bound, we define an edge-specific KC score that quantifies each edge's structural influence via its induced change in GKC. KCES then identifies and prunes high-KC edges, which are empirically enriched with adversarial perturbations under structural attacks, to mitigate their harmful impact. Computationally efficient and scalable, KCES operates as a lightweight preprocessing step without retraining and can be seamlessly integrated with existing defenses. Extensive experiments demonstrate that KCES consistently outperforms representative robust baselines across diverse attack settings and scales effectively to large graphs. Supported by theoretical analysis and extensive empirical validation, KCES provides a principled and efficient framework for securing GNNs. Our code is available at https://github.com/karpning/KCScore.
Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.