Certifying Robustness of Convolutional Neural Networks with Tight Linear Approximation

1 code implementation • 13 Nov 2022 • Yuan Xiao, Tongtong Bai, Mingzheng Gu, Chunrong Fang, Zhenyu Chen

The robustness of neural network classifiers is becoming important in the safety-critical domain and can be quantified by robustness verification.