As we seek to deploy machine learning models beyond virtual and controlled domains, it is critical to analyze not only the accuracy or the fact that it works most of the time, but if such a model is truly robust and reliable. This paper studies strategies to implement adversary robustly trained algorithms towards guaranteeing safety in machine learning algorithms. We provide a taxonomy to classify adversarial attacks and defenses and formulate for the Robust Optimization problem in a min-max setting, and divide it into 3 subcategories, namely: Adversarial (re)Training, Regularization Approach, and Certified Defenses. We survey the most recent and important results in adversarial example generation and defense mechanisms with adversarial (re)Training as their main defense against perturbations or add regularization terms which change the behavior of the gradient, making it harder for attackers to achieve their objective. Alternatively, we've surveyed methods which formally derive certificates of robustness by exactly solving the optimization problem or by approximations using upper or lower bounds. In addition, we discussed the challenges faced by most of the recent algorithms presenting future research perspectives.

本篇研究通过分类对抗性攻击和防御方法，提出三类半定界数理优化问题，即对抗(再)训练、正则化方法和认证防御，并调查了最近的研究成果和挑战以及展望未来的发展。

深度学习中对抗鲁棒性的机遇与挑战：综述