用概率抽象解释分析神经网络输入分布，无需穷举所有输入。
Probabilistic Abstract Interpretation on Neural Networks via Grids Approximation
- 基于网格逼近构建概率抽象解释框架
- 可处理无穷多输入下的密度传播问题
- 适用于安全验证与不确定性分析场景
概率抽象解释是一种在无法测试所有输入时提取程序特性的理论。本文将其应用于神经网络，以分析当网络存在不可数或可数无穷多个输入时，所有可能输入的密度分布传播。我们展示了该理论框架在神经网络中的实现方式，并讨论了不同的抽象域及其对应的Moore-Penrose伪逆和抽象变换器。同时通过实验案例说明该框架如何帮助解决实际问题。
原文摘要 · Abstract (English)
Probabilistic abstract interpretation is a theory used to extract particular properties of a computer program when it is infeasible to test every single inputs. In this paper we apply the theory on neural networks for the same purpose: to analyse density distribution flow of all possible inputs of a neural network when a network has uncountably many or countable but infinitely many inputs. We show how this theoretical framework works in neural networks and then discuss different abstract domains and corresponding Moore-Penrose pseudo-inverses together with abstract transformers used in the framework. We also present experimental examples to show how this framework helps to analyse real world problems.
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。