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.

通过特征基对抗攻击研究了图在现代社交媒体和学术应用中所具有的复杂网络，并侧重于决策时攻击和毒化攻击，与 Net Attack 和 Meta Attack 等现有模型不同，我们的研究专门针对节点属性。利用 Hellaswag 文本数据集和 Cora 以及 CiteSeer 图数据集进行了分析，结果发现使用投影梯度下降的决策时攻击比使用平均节点嵌入和图对比学习策略的毒化攻击更强大，这为图数据安全提供了启示，指出了图模型最脆弱的部分，从而推动了对此类攻击的更强大防御机制的开发。