提出两种新方法分析神经网络输入分布流。
Distribution and Clusters Approximations as Abstract Domains in Probabilistic Abstract Interpretation to Neural Network Analysis
- 用分布和聚类近似替代网格抽象
- 理论推导出对应的抽象变换器
- 适合做神经网络形式化验证的研究者
概率抽象解释框架通过分析神经网络所有可能输入的密度分布流来实现分析。网格近似是该框架使用的抽象域之一，将具体空间划分为网格。本文引入两种新近似方法：分布近似和聚类近似，并借助简单示例图示，理论上说明了这两种方法如何工作，以及相应的抽象变换器的设计原理。
原文摘要 · Abstract (English)
The probabilistic abstract interpretation framework of neural network analysis analyzes a neural network by analyzing its density distribution flow of all possible inputs. The grids approximation is one of abstract domains the framework uses which abstracts concrete space into grids. In this paper, we introduce two novel approximation methods: distribution approximation and clusters approximation. We show how these two methods work in theory with corresponding abstract transformers with help of illustrations of some simple examples.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。