Experimental results of momentum gradients.

In the context of existing adversarial attack schemes based on unsupervised graph contrastive learning, a common issue arises due to the discreteness of graph structures, leading to reduced reliability of structural gradients and consequently resulting in the problem of attacks getting trapped in local optima. An adversarial attack method based on momentum gradient candidates is proposed in this research. Firstly, the gradients obtained by back-propagation are transformed into momentum gradients, and the gradient update is guided by overlaying the previous gradient information in a certain proportion to accelerate convergence speed and improve the accuracy of gradient update. Secondly, the exploratory process of candidate and evaluation is carried out by summing the momentum gradients of the two views and ranking them in descending order of saliency. In this process, selecting adversarial samples with stronger perturbation effects effectively improves the success rate of adversarial attacks. Finally, extensive experiments were conducted on three different datasets, and our generated adversarial samples were evaluated against contrastive learning models across two downstream tasks. The results demonstrate that the attack strategy proposed outperforms existing methods, significantly improving convergence speed. In the link prediction task, targeting the Cora dataset with perturbation rates of 0.05 and 0.1, the attack performance outperforms all baseline tasks, including the supervised baseline methods. The attack method is also transferred to other graph representation models, validating the method’s strong transferability.

针对现有基于无监督图对比学习（unsupervised graph contrastive learning）的对抗攻击（adversarial attack）方案，由于图结构的离散性，普遍存在结构梯度可靠性降低的问题，进而导致攻击陷入局部最优的困境。本研究提出一种基于动量梯度候选的对抗攻击方法。首先，将反向传播（back-propagation）得到的梯度转换为动量梯度（momentum gradients），通过按一定比例叠加历史梯度信息指导梯度更新，以加快收敛速度并提升梯度更新的精度。其次，通过对两个视图的动量梯度求和并按显著性降序排序，完成候选样本的探索与评估流程；在此过程中，选取扰动效果更强的对抗样本，可有效提升对抗攻击的成功率。最后，在三个不同数据集上开展了大量实验，并针对两种下游任务的对比学习模型，对本研究生成的对抗样本进行了评估。实验结果表明，所提攻击策略优于现有方法，可显著提升收敛速度。在链接预测（link prediction）任务中，针对扰动率为0.05和0.1的Cora数据集，本方法的攻击性能优于所有基线方法，包括有监督基线方法。此外，本攻击方法还可迁移至其他图表示模型（graph representation models），验证了其较强的迁移性能。