面向图神经网络的对抗攻击与防御综述 |
| |
作者姓名: | 陈晋音 张敦杰 黄国瀚 林翔 鲍亮 |
| |
作者单位: | 1. 浙江工业大学网络空间安全研究院,浙江 杭州 310023;2. 浙江工业大学信息工程学院,浙江 杭州 310023;3. 信息网络安全公安部重点实验室,上海 200000 |
| |
基金项目: | 国家自然科学基金(62072406);浙江省自然科学基金(LY19F020025);信息网络安全公安部重点实验室开放课题项目(C20604) |
| |
摘 要: | 面向已有的图神经网络的攻击与防御方法,较全面地综述了图神经网络对抗攻防技术与鲁棒性分析。首先,综述了图神经网络在不同任务下的对抗攻击与基于不同策略的防御方法,并全面介绍了鲁棒性分析技术;随后,介绍了常用的基准数据集与评价指标;最后,提出了未来可能的研究方向和发展趋势。
|
关 键 词: | 图神经网络 对抗攻击 防御算法 鲁棒性分析 |
Adversarial attack and defense on graph neural networks: a survey |
| |
Authors: | Jinyin CHEN Dunjie ZHANG Guohan HUANG Xiang LIN Liang BAO |
| |
Affiliation: | 1. Institute of Cyberspace Security, Zhejiang University of Technology, Hangzhou 310023, China;2. The College of Information Engineering, Zhejiang University of Technology, Hangzhou 310023, China;3. Key Lab of Information Network Security, Ministry of Public Security, Shanghai 200000, China |
| |
Abstract: | For the numerous existing adversarial attack and defense methods on GNN, the main adversarial attack and defense algorithms of GNN were reviewed comprehensively, as well as robustness analysis techniques.Besides, the commonly used benchmark datasets and evaluation metrics in the security research of GNN were introduced.In conclusion, some insights on the future research direction of adversarial attacks and the trend of development were put forward. |
| |
Keywords: | graph neural networks adversarial attack defense algorithms robustness analysis |
本文献已被 维普 等数据库收录! |
| 点击此处可从《》浏览原始摘要信息 |
|
点击此处可从《》下载全文 |
|