12. 参考文献
AISECjp
・Stealing Machine Learning Models via Prediction APIs
https://arxiv.org/abs/1609.02943
・Simple Black-Box Adversarial Perturbations for Deep Networks
https://arxiv.org/abs/1612.06299
・Vulnerability of Deep Reinforcement Learning to Policy Induction Attacks
https://arxiv.org/abs/1701.04143
・現実世界での機械学習によるアノマリ検知システムの構築と回避
https://www.slideshare.net/codeblue_jp/by-clarence-chio-code-blue-2015
・ The Pursuit of Exploitable Bugs in Machine Learning
https://arxiv.org/abs/1701.04739