Ian Goodfellow and Jonathon Shlens and Christian Szegedy, Explaining and Harnessing Adversarial Examples. International Conference on Learning Representations, 2015.
 Guyen, A., J. Yosinski, and J. Clune, Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. 2015: p. 427-436.
 Moosavi Dezfooli, Seyed Mohsen and Fawzi, Alhussein and Frossard, Pascal, DeepFool: a simple and accurate method to fool deep neural networks, Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
 Weilin Xu, Yanjun Qi, and David Evans, Automatically Evading Classifiers A Case Study on PDF Malware Classifiers, NDSS, 2016
 Qixue Xiao, Kang Li, Deyue Zhang, and Weilin Xu, Security Risks in Deep Learning Implementations, arXiv:1711.11008. https://arxiv.org/abs/1711.11008, 2017
 Qixue Xiao, Kang Li, Deyue Zhang, and Yier Jin, The Downscaling Attack Against Deep Learning Applications, arXiv:1711.11008. https://arxiv.org/abs/1712.07805, 2017
 Richard Chirgwin, What do TensorFlow, Caffe, and Torch have in Common? Open CVEs. https://www.theregister.co.uk/2017/11/30/machine_learning_vulnerabilities/ 2017