Graphs are commonly used to model complex networks prevalent in modern social media and literacy applications. Our research investigates the vulnerability of these graphs through the application of feature based adversarial attacks, focusing on both decision time attacks and poisoning attacks. In contrast to state of the art models like Net Attack and Meta Attack, which target node attributes and graph structure, our study specifically targets node attributes. For our analysis, we utilized the text dataset Hellaswag and graph datasets Cora and CiteSeer, providing a diverse basis for evaluation. Our findings indicate that decision time attacks using Projected Gradient Descent (PGD) are more potent compared to poisoning attacks that employ Mean Node Embeddings and Graph Contrastive Learning strategies. This provides insights for graph data security, pinpointing where graph-based models are most vulnerable and thereby informing the development of stronger defense mechanisms against such attacks.

翻译：图结构常用于建模现代社交媒体与文本分析应用中普遍存在的复杂网络。本研究通过应用基于特征的对抗性攻击（聚焦决策时攻击与投毒攻击两种类型），探究此类图结构的脆弱性。与同时针对节点属性与图结构的Net Attack、Meta Attack等先进模型不同，本研究专门针对节点属性展开。分析过程中，我们采用文本数据集Hellaswag以及图数据集Cora和CiteSeer作为多样化的评估基础。研究结果表明，使用投影梯度下降（PGD）的决策时攻击比采用平均节点嵌入和图对比学习策略的投毒攻击更具破坏力。该发现为图数据安全提供了洞见，精准揭示了图模型最易受攻击的薄弱环节，进而为针对此类攻击开发更强的防御机制提供了依据。