Unnoticeable Backdoor Attacks on Graph Neural Networks

Author:

Dai Enyan1ORCID,Lin Minhua1ORCID,Zhang Xiang1ORCID,Wang Suhang1ORCID

Affiliation:

1. Pennsylvania State University, USA

Funder

National Science Foundation

Department of Homeland Security (DNS) CINA

Army Research Office

Publisher

ACM

Reference46 articles.

1. Aleksandar Bojchevski and Stephan Günnemann . 2019 . Adversarial Attacks on Node Embeddings via Graph Poisoning . In Proceedings of the 36th International Conference on Machine Learning, ICML(Proceedings of Machine Learning Research). PMLR. Aleksandar Bojchevski and Stephan Günnemann. 2019. Adversarial Attacks on Node Embeddings via Graph Poisoning. In Proceedings of the 36th International Conference on Machine Learning, ICML(Proceedings of Machine Learning Research). PMLR.

2. Molecular generative Graph Neural Networks for Drug Discovery

3. A Restricted Black-Box Adversarial Framework Towards Attacking Graph Embedding Models

4. Ming Chen Zhewei Wei Zengfeng Huang Bolin Ding and Yaliang Li. 2020. Simple and deep graph convolutional networks. In ICML. 1725–1735. Ming Chen Zhewei Wei Zengfeng Huang Bolin Ding and Yaliang Li. 2020. Simple and deep graph convolutional networks. In ICML. 1725–1735.

5. Yongqiang Chen Han Yang Yonggang Zhang MA KAILI Tongliang Liu Bo Han and James Cheng. 2022. Understanding and Improving Graph Injection Attack by Promoting Unnoticeability. In ICLR. Yongqiang Chen Han Yang Yonggang Zhang MA KAILI Tongliang Liu Bo Han and James Cheng. 2022. Understanding and Improving Graph Injection Attack by Promoting Unnoticeability. In ICLR.

Cited by 9 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Crucial rather than random: Attacking crucial substructure for backdoor attacks on graph neural networks;Engineering Applications of Artificial Intelligence;2024-10

2. Cross-Context Backdoor Attacks against Graph Prompt Learning;Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining;2024-08-24

3. Rethinking Graph Backdoor Attacks: A Distribution-Preserving Perspective;Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining;2024-08-24

4. Multi-target label backdoor attacks on graph neural networks;Pattern Recognition;2024-08

5. An Imperceptible and Owner-unique Watermarking Method for Graph Neural Networks;ACM Turing Award Celebration Conference 2024;2024-07-05

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3