{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T03:54:47Z","timestamp":1787025287949,"version":"3.56.0"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,8]]},"abstract":"<jats:p>Graph neural networks (GNNs) which apply the deep neural networks to graph data have achieved significant performance for the task of semi-supervised node classification. However, only few work has addressed the adversarial robustness of GNNs. In this paper, we first present a novel gradient-based attack method that facilitates the difficulty of tackling discrete graph data. When comparing to current adversarial attacks on GNNs, the results show that by only perturbing a small number of edge perturbations, including addition and deletion, our optimization-based attack can lead to a noticeable decrease in classification performance. Moreover, leveraging our gradient-based attack, we propose the first optimization-based adversarial training for GNNs. Our method yields higher robustness against both different gradient based and greedy attack methods without sacrifice classification accuracy on original graph.<\/jats:p>","DOI":"10.24963\/ijcai.2019\/550","type":"proceedings-article","created":{"date-parts":[[2019,7,28]],"date-time":"2019-07-28T03:46:05Z","timestamp":1564285565000},"page":"3961-3967","source":"Crossref","is-referenced-by-count":232,"title":["Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective"],"prefix":"10.24963","author":[{"given":"Kaidi","family":"Xu","sequence":"first","affiliation":[{"name":"Electrical & Computer Engineering, Northeastern University, Boston, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongge","family":"Chen","sequence":"additional","affiliation":[{"name":"Electrical Engineering & Computer Science, Massachusetts Institute of Technology, Cambridge, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sijia","family":"Liu","sequence":"additional","affiliation":[{"name":"MIT-IBM Watson AI Lab, IBM Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pin-Yu","family":"Chen","sequence":"additional","affiliation":[{"name":"MIT-IBM Watson AI Lab, IBM Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tsui-Wei","family":"Weng","sequence":"additional","affiliation":[{"name":"Electrical Engineering & Computer Science, Massachusetts Institute of Technology, Cambridge, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingyi","family":"Hong","sequence":"additional","affiliation":[{"name":"Electrical & Computer Engineering, University of Minnesota, Minneapolis, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xue","family":"Lin","sequence":"additional","affiliation":[{"name":"Electrical & Computer Engineering, Northeastern University, Boston, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10584","event":{"name":"Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}","theme":"Artificial Intelligence","location":"Macao, China","acronym":"IJCAI-2019","number":"28","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2019,8,10]]},"end":{"date-parts":[[2019,8,16]]}},"container-title":["Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2019,7,28]],"date-time":"2019-07-28T03:50:04Z","timestamp":1564285804000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2019\/550"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2019\/550","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}