用采样法验证神经网络输出概率满足性并自动调整约束集
SAVER: A Toolbox for Sampling-Based, Probabilistic Verification of Neural Networks
- 基于采样和符号距离函数判断输出是否在目标集合内
- 可计算输出落入指定集合的概率，并保证达到用户设定的置信水平
- 适合需要可靠性保障的AI系统验证，如自动驾驶安全检测
我们提出一个神经网络验证工具箱，用于1）评估神经网络在给定输入分布下满足约束条件的概率，2）合成一组扩展因子以实现预定的满足概率。该工具箱通过用户指定的置信水平，判断神经网络输出是否可能落在给定集合中。若确定当前集合无法满足概率约束，则工具箱采用本文提出的方法调整约束集合，确保达成用户定义的满足概率。工具箱基于采样方法，利用符号距离函数的性质来定义集合包含关系。
原文摘要 · Abstract (English)
We present a neural network verification toolbox to 1) assess the probability of satisfaction of a constraint, and 2) synthesize a set expansion factor to achieve the probability of satisfaction. Specifically, the tool box establishes with a user-specified level of confidence whether the output of the neural network for a given input distribution is likely to be contained within a given set. Should the tool determine that the given set cannot satisfy the likelihood constraint, the tool also implements an approach outlined in this paper to alter the constraint set to ensure that the user-defined satisfaction probability is achieved. The toolbox is comprised of sampling-based approaches which exploit the properties of signed distance function to define set containment.
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。