DeepAbstract: Neural Network Abstraction for Accelerating Verification

ATVA(2020)

引用 30|浏览9
暂无评分
摘要
While abstraction is a classic tool of verification to scale it up, it is not used very often for verifying neural networks. However, it can help with the still open task of scaling existing algorithms to state-of-the-art network architectures. We introduce an abstraction framework applicable to fully-connected feed-forward neural networks based on clustering of neurons that behave similarly on some inputs. For the particular case of ReLU, we additionally provide error bounds incurred by the abstraction. We show how the abstraction reduces the size of the network, while preserving its accuracy, and how verification results on the abstract network can be transferred back to the original network.
更多
查看译文
关键词
neural network abstraction,verification,neural network
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络