arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.18136cs.LGcs.AI
收藏

在图神经网络训练中识别被篡改的图:基于解释的方法与新指标

Identifying Backdoored Graphs in Graph Neural Network Training: An Explanation-Based Approach with Novel Metrics

Illinois Institute of Technology(伊利诺伊理工学院)

Jane Downer, Ren Wang, Binghui Wang

AI总结:

本文提出基于图级解释的新方法,通过提取和转换GNN解释机制的二次输出,开发了七种创新指标以有效检测图神经网络的后门攻击,并通过多个基准数据集验证了方法的有效性。

摘要:

图神经网络(GNNs)在众多领域中受到欢迎,但它们容易受到后门攻击,这些攻击可能破坏其性能和伦理应用。检测这些攻击对于保持GNN分类任务的可靠性和安全性至关重要,但现有方法往往缺乏灵活性,依赖单一指标,无法捕捉到后门行为的全部范围。为了解决这一挑战,我们设计了一种新颖的检测方法,创造性地利用图级解释。通过提取和转换GNN解释机制的二次输出,我们开发了七种创新指标,以有效检测GNN上的后门攻击。此外,我们还开发了一种自适应攻击以严格评估我们的方法。我们测试了我们的方法在多个基准数据集上的表现,并检查其对各种攻击模型的有效性。我们的结果表明,我们的方法能够实现高检测性能,标志着在保护GNN免受后门攻击方面的重大进展。

英文摘要:

Graph Neural Networks (GNNs) have gained popularity in numerous domains, yet they are vulnerable to backdoor attacks that can compromise their performance and ethical application. The detection of these attacks is crucial for maintaining the reliability and security of GNN classification tasks, but existing methods are often inflexible, relying on single metrics that fail to capture the full range of backdoor behaviors. Recognizing the challenge in detecting such intrusions, we devised a novel detection method that creatively leverages graph-level explanations. By extracting and transforming secondary outputs from GNN explanation mechanisms, we developed seven innovative metrics for effective detection of backdoor attacks on GNNs. Additionally, we develop an adaptive attack to rigorously evaluate our approach. We test our method on multiple benchmark datasets and examine its efficacy against various attack models. Our results show that our method can achieve high detection performance, marking a significant advancement in safeguarding GNNs against backdoor attacks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑