DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Yang, Eunho | - |
dc.contributor.advisor | 양은호 | - |
dc.contributor.author | Bae, Seohui | - |
dc.date.accessioned | 2023-06-22T19:31:14Z | - |
dc.date.available | 2023-06-22T19:31:14Z | - |
dc.date.issued | 2022 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=997674&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/308186 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 김재철AI대학원, 2022.2,[iii, 23 p. :] | - |
dc.description.abstract | Small perturbations of graph structure have been verified to bring catastrophically performance degradation of most Graph Neural Networks (GNNs). Existing defenses of which mainly top on homophily assumption could not address all structural attacks and do not perform reasonable robustness on graphs in general. An empirical analysis on structural attack motivated us in that an effective structure attack primarily injects edges adjusting local heterophily level as well as distance in feature space. While raising the potential problem of un-screening and mis-screening of homophily-based works for the first time, we propose a novel framework that resolves the issues and thereby elevating the robustness of GNN. Experiments on a variety of attack settings, datasets, and base architecture have shown that incorporating GNN with our framework adequately restores its demolished performance and accomplishes to outperform the existing baselines, improving the robustness of structural perturbations on a homophilous graph (Cora) by %3 and a heterophyllous graph (Wisconsin) by 9% | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.title | Robustness of adversarial attacks on GNN based on global heterophily level | - |
dc.title.alternative | 그래프의 이종선호 정도에 기반한 그래프 적대적 공격 방어 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :김재철AI대학원, | - |
dc.contributor.alternativeauthor | 배서희 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.