.png){kind=icon}
返回
A Clean-Label Graph Backdoor Attack Method in Node Classification Task
.png){kind=icon}
OA
AI
DOI：10.1016/j.knosys.2024.112433.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Backdoor attacks in the traditional graph neural networks (GNNs) field are easily detectable due to the dilemma of confusing labels. To explore the backdoor vulnerability of GNNs and create a more stealthy backdoor attack method, a clean-label graph backdoor attack method(CGBA) in the node classification task is proposed in this paper. Differently from existing backdoor attack methods, CGBA requires neither modification of node labels nor graph structure. Specifically, to solve the problem of inconsistency between the contents and labels of the samples, CGBA selects poisoning samples in a specific target class and uses the samples' own label as the target label (i.e., clean-label) after injecting triggers into the target samples. To guarantee the similarity of neighboring nodes, the raw features of the nodes are elaborately picked as triggers to further improve the concealment of the triggers. Extensive experiments results show the effectiveness of our method. When the poisoning rate is 0.04, CGBA can achieve an average attack success rate of 87.8%, 98.9%, 89.1%, and 98.5%, respectively.
Keyword:
Machine learning
Network security
Graph neural networks
Backdoor
Node classification
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
K
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Not All Samples Are Born Equal: Towards Effective Clean-Label Backdoor Attacks.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏分享收藏Combining HF rTMS over the Left DLPFC with Concurrent Cognitive Activity for the Offline Modulation of Working Memory in Healthy Volunteers: A Proof-of-Concept Study将左侧DLPFC上的HF rTMS与同时进行的认知活动相结合，以离线调节健康志愿者的工作记忆: 一项概念验证研究OAAI
OAAI分享收藏
PoisonedGNN: Backdoor Attack on Graph Neural Networks-Based Hardware Security SystemsPoisonedGNN: 基于图神经网络的硬件安全系统后门攻击
PREAI
分享收藏 没有更多内容
没有更多内容