This repository replicates the code and results of the paper "Simple Black-box Adversarial Attacks". The original code can be found here.
The idea is to not to blindly copy the official code of the authors, but to implement it independently.
- The paper from Guo et al.
- Label index conversion from the official ImageNet to the indices which were used to pre-train the PyTorch ResNet50; by GitHub user raghakot File/Repo