1. Good word attacks on statistical spam filters;lowd;Proc CEAS,2005
2. Benchmarking neural network robustness to common corruptions and perturbations;hendrycks;Proc Int Conf Learn Represent,2019
3. Adversarial learning
4. Torchattacks: A PyTorch repository for adversarial attacks;kim;arXiv 2010 01950,2020
5. Explaining and harnessing adversarial examples;goodfellow;arXiv 1412 6572,2014