Knowledge graphs represent factual knowledge about the world as relationships between concepts and are critical for intelligent decision making in enterprise applications. New knowledge is inferred from the existing facts in the knowledge graphs by encoding the concepts and relations into low-dimensional feature vector representations. The most effective representations for this task, called Knowledge Graph Embeddings (KGE), are learned through neural network architectures. Due to their impressive predictive performance, they are increasingly used in high-impact domains like healthcare, finance and education. However, are the black-box KGE models adversarially robust for use in domains with high stakes? This thesis argues that state-of-the-art KGE models are vulnerable to data poisoning attacks, that is, their predictive performance can be degraded by systematically crafted perturbations to the training knowledge graph. To support this argument, two novel data poisoning attacks are proposed that craft input deletions or additions at training time to subvert the learned model's performance at inference time. These adversarial attacks target the task of predicting the missing facts in knowledge graphs using KGE models, and the evaluation shows that the simpler attacks are competitive with or outperform the computationally expensive ones. The thesis contributions not only highlight and provide an opportunity to fix the security vulnerabilities of KGE models, but also help to understand the black-box predictive behaviour of KGE models.
翻译:知识图表代表着关于世界的事实知识,认为世界是概念之间的关系,对于企业应用中的明智决策至关重要。新知识通过将概念和关系编码为低维特征矢量示意图,从知识图表中的现有事实中推断出来。这一任务的最有效表现,即称为知识图嵌入(KGE),是通过神经网络结构学习的。由于其令人印象深刻的预测性能,它们越来越多地用于保健、财政和教育等影响较大的领域。然而,黑盒 KGE 模型是否对抗性强,用于利益攸关的领域?这个理论认为,最先进的KGE模型很容易受到数据中毒攻击,也就是说,其预测性能可以通过系统设计对培训知识图的干扰而降低。为支持这一论点,建议两项新的数据中毒攻击在培训时间进行人工输入删除或添加,以颠覆所学模型在推论时间的性能。这些对抗性攻击的目标是用KGE模型预测缺失的事实数据图表,而这种评价显示,更简单的KGEGE模型可以有竞争力,但只能显示,更简单的攻击行为模式能够使KGEGE模型更能评估一个昂贵的可能性。