NF-GNN:Network Flow Graph Neural Networks for Malware Detection and Classification. (不是CFG) 本文提出CFGExpaliner,是首个针对基于GNN进行恶意软件分类(注意不是检测)的可解释性工作。CFGExplainer在CFG中提取出得到分类结果的关键子图,并对子图内节点进行重要性排序。作者通过与三个常见的GNN解释方法:GNN...
GNNs combine node features, connection patterns, and graph structure by using a neural network to embed node information and pass it through edges in the graph. We want to identify the patterns in the input data used by the GNN model to make a decision and examine if the model works as ...
研究网络安全领域AI可解释性的工作还有Euro S&P上的《Evaluating Explanation Methods for Deep Learning in Security》,本文则主要是针对带有结构信息的图数据以及漏洞发现场景。 图神经网络在漏洞发现中的应用 源代码可以自然转化为多种有向图模型,例如: AST(抽象语法树),程序的语法结构,节点为程序语言符号,边为语法...
2.2Explanation via Feature Information 2.3 Multi-instance explanations through graph prototypes 3. Experiments 4. Conclusion 1.Introduction 图神经网络(Graph Neural Network), 作为深度学习领域最热门的方向之一,相关论文在各大顶会层出不穷. 但是,图神经网络的解释性问题没有得到较多的关注.图神经网络的解释性是...
CGMega detects gene modules based on a model-agnostic neural network interpretation approach (Fig.1b), and these gene modules consist of two parts: i) a core subgraph consisting of the most influential pairwise relationships for the prediction of cancer gene, and ii) 15-dimensional importance ...
Thus,many methods have been proposed to interpreta trained GNN [2].The widely used GNN explanation methodis GNNExplainer [3], which optimizes an edgemask such that the mutual information be-tween the masked graph and the predictionis maximized when the size of the edge maskis constrained. PG...
Graph Neural Networks (GNNs) are a powerful tool for machine learning on graphs.GNNs combine node feature information with the graph structure by recursively passing neural messages along edges of the input graph. However, incorporating both graph structure and feature information leads to complex mode...
内容提示: GNNExplainer: Generating Explanationsfor Graph Neural NetworksRex Ying † Dylan Bourgeois †,‡ Jiaxuan You † Marinka Zitnik † Jure Leskovec †† Department of Computer Science, Stanford University‡ Robust.AI{rexying, dtsbourg, jiaxuan, marinka, jure}@cs.stanford.edu...
We provide a concise explanation of their underlying principles to establish a solid understanding that will serve as a basis for exploring the applications of GNNs in mechanics-related domains. The scope of this paper is intended to cover the categorisation of literature into solid mechanics, fluid...
The masking approach is also found in Neural Relational Inference 22, albeit with different motivation and objective. Lastly, we remove low values inMthrough thresholding and compute the element-wise multiplication of(M)andAc to arrive at the explanation GSfor GNNs prediction y at node v. 4.2...