图 书 馆
神经网络对图数据的对抗攻击Adversarial Attacks on Neural Networks for Graph Data |
|
| 课程网址: | http://videolectures.net/kdd2018_zuegner_adversarial_networks/ |
| 主讲教师: | Daniel Zügner |
| 开课单位: | 慕尼黑大学 |
| 开课时间: | 2018-11-23 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | Deep learning models for graphs have achieved strong performance for the task of node classification. Despite their proliferation, currently there is no study of their robustness to adversarial attacks. Yet, in domains where they are likely to be used, e.g. the web, adversaries are common. Can deep learning models for graphs be easily fooled? In this work, we introduce the first study of adversarial attacks on attributed graphs, specifically focusing on models exploiting ideas of graph convolutions. In addition to attacks at test time, we tackle the more challenging class of poisoning/causative attacks, which focus on the training phase of a machine learning model. We generate adversarial perturbations targeting the node’s features and the graph structure, thus, taking the dependencies between instances in account. Moreover, we ensure that the perturbations remain unnoticeable by preserving important data characteristics. To cope with the underlying discrete domain we propose an efficient algorithm Nettack exploiting incremental computations. Our experimental study shows that accuracy of node classification significantly drops even when performing only few perturbations. Even more, our attacks are transferable: the learned attacks generalize to other state-of-the-art node classification models and unsupervised approaches, and likewise are successful even when only limited knowledge about the graph is given. |
| 关 键 词: | 深度学习模型; 对属性图; 对抗性扰动; 节点分类模型 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2022-11-23：chenjy |
| 最后编审: | 2022-11-23：chenjy |
| 阅读次数: | 37 |