链接预测对抗攻击
Link Prediction Adversarial Attack
摘要:
深度神经网络在解决计算机视觉和一些图进化任务(如节点分类和链接预测)方面表现出了卓越的性能。然而,各种对抗性攻击方法生成的精心设计的对抗性示例也揭示了深度模型的脆弱性。随着深度模型在复杂网络分析中的广泛应用,本文定义并描述了链接预测对抗攻击问题,并提出了一种基于训练图自动编码器(GAE)中梯度信息的迭代梯度攻击(IGA)。据我们所知,这是第一次链接预测对抗攻击问题的定义和攻击方法提出。毫不奇怪,GAE很容易被对抗网络欺骗,在干净的网络上只有少数链接受到干扰。通过对不同的真实世界数据集进行全面的实验,我们可以得出结论,大多数基于深度模型和其他最先进的链接预测算法都无法像GAE一样逃脱对抗性攻击。一方面可以使攻击作为一种有效的隐私保护工具,避免链接预测的未知侵犯,另一方面,链接预测攻击可以作为现有链接预测算法攻击防御性的鲁棒性评价指标。
英文摘要:
Deep neural network has shown remarkable performance in solving computer vision and some graph evolved tasks, such as node classification and link prediction. However, the vulnerability of deep model has also been revealed by carefully designed adversarial examples generated by various adversarial attack methods. With the wider application of deep model in complex network analysis, in this paper we define and formulate the link prediction adversarial attack problem and put forward a novel iterative gradient attack (IGA) based on the gradient information in trained graph auto-encoder (GAE). To our best knowledge, it is the first time link prediction adversarial attack problem is defined and attack method is brought up. Not surprisingly, GAE was easily fooled by adversarial network with only a few links perturbed on the clean network. By conducting comprehensive experiments on different real-world data sets, we can conclude that most deep model based and other state-of-art link prediction algorithms cannot escape the adversarial attack just like GAE. We can benefit the attack as an efficient privacy protection tool from link prediction unknown violation, on the other hand, link prediction attack can be a robustness evaluation metric for current link prediction algorithm in attack defensibility.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。