Global robustness evaluation of deep neural networks with provable guarantees for the Hamming distance

Deployment of deep neural networks (DNNs) in safety-critical systems requires provable guarantees for their correct behaviours. We compute the maximal radius of a safe norm ball around a given input, within which there are no adversarial examples for a trained DNN. We define global robustness as an...

Mô tả đầy đủ

Chi tiết về thư mục
Những tác giả chính: Ruan, W, Wu, M, Sun, Y, Huang, X, Kroening, D, Kwiatkowska, M
Định dạng: Conference item
Được phát hành: International Joint Conferences on Artificial Intelligence Organization 2019