Xiaowei Huang, Marta Kwiatkowska, Sen Wang, Min Wu
TL;DR本研究提出一种基于 Satisfiability Modulo Theory (SMT) 的新型自动化验证框架,旨在保证深度神经网络对于图像操作的安全性,能够发现对于给定操作范围和家族,对抗性样本是否存在,同时比较现有的相关技术。
Abstract
deep neural networks have achieved impressive experimental results in image
classification, but can surprisingly be unstable with respect to adversarial
perturbations, that is, minimal changes to the input image that cause the
network to misclassify it. With potential applications incl