基于图神经网络的知识图谱问答（KGQA）的查询侧攻击：从实体链接到答案生成的失败溯源

中文摘要 AI 辅助

基于图神经网络（GNN）的知识图谱问答（KGQA）流水线通过四个离散阶段处理查询：实体链接、子图检索、GNN推理和答案生成。标准鲁棒性评估将阶段级失败混为单一的端到端指标，掩盖了脆弱性来源和适当的缓解目标。我们探究当流水线受到输入问题的对抗扰动时，哪个阶段会失败以及为何失败。我们引入一种阶段隔离协议，该协议包含两种经知识图谱验证的保留答案的对抗扰动：组合重构（CR）和关系同义词交换（RS），二者针对不同阶段且保留实体种子。在ComplexWebQuestions和WebQSP数据集上的评估结果与普遍假设相悖：当子图完整时，GNN推理阶段保留接近基线的准确率；而在CR攻击下，子图构建占端到端崩溃的99%以上，即使检索到的子图中有74%包含正确答案，该情况仍会发生。这揭示了端到端指标无法检测到的答案存在性与可达性之间的根本区别，并将缓解目标明确指向子图构建阶段而非推理模型。受扰动的数据集和评估基础设施已在该httpsURL发布。

英文摘要

GNN-based Knowledge Graph Question Answering (KGQA) pipelines process queries through four discrete stages: entity linking, subgraph retrieval, GNN reasoning, and answer generation. Standard robustness evaluations conflate stage-level failures into a single end-to-end metric, obscuring both the source of brittleness and the appropriate mitigation target. We ask which stage fails, and why, when the pipeline is subjected to adversarial perturbations on the input question. We introduce a stage-isolation protocol with two answer-preserving adversarial perturbations verified against the knowledge graph: Compositional Restructuring (CR) and Relation Synonym Swap (RS) target distinct stages while leaving entity seeds intact. Evaluated across ComplexWebQuestions and WebQSP, the results run counter to prevailing assumptions: the GNN reasoning stage retains near-baseline accuracy when the subgraph is intact, while subgraph construction accounts for over 99\% of the end-to-end collapse under CR, occurring even when the gold answer is present in 74\% of retrieved subgraphs. This exposes a fundamental distinction between answer presence and answer reachability that end-to-end metrics cannot detect, and places the mitigation target firmly at the subgraph construction stage rather than the reasoning model. Perturbed datasets and evaluation infrastructure are released at https://anonymous.4open.science/r/atkgrag-E85C .

发表机构

• National Institute of Science Education and Research（国家科学教育与研究学院）
• Homi Bhabha National Institute（霍米·巴巴国家学院）

机构由 AI 辅助整理，请以论文原文为准。