State-of-the-art machine learning models can be vulnerable to very small input perturbations that are adversarially constructed. Adversarial training is an effective approach to defend against such examples. It is formulated as a min-max problem, searching for the best solution when the training data was corrupted by the worst-case attacks. For linear regression problems, adversarial training can be formulated as a convex problem. We use this reformulation to make two technical contributions: First, we formulate the training problem as an instance of robust regression to reveal its connection to parameter-shrinking methods, specifically that $\ell_\infty$-adversarial training produces sparse solutions. Secondly, we study adversarial training in the overparameterized regime, i.e. when there are more parameters than data. We prove that adversarial training with small disturbances gives the solution with the minimum-norm that interpolates the training data. Ridge regression and lasso approximate such interpolating solutions as their regularization parameter vanishes. By contrast, for adversarial training, the transition into the interpolation regime is abrupt and for non-zero values of disturbance. This result is proved and illustrated with numerical examples.
翻译:最先进的机器学习模式很容易受到极小的投入干扰,这种干扰是对抗性构筑的。 反向培训是抵御这类例子的有效方法。 它是一个微轴问题,在培训数据被最坏的攻击腐蚀时寻找最佳解决办法。 对于线性回归问题,对抗性培训可以被发展成一个螺旋问题。 我们利用这一重新拟订方法作出两项技术贡献: 首先,我们将培训问题作为强力回归的例子,以揭示其与参数缩小方法的联系,特别是$\ell ⁇ infty$-对抗性培训产生稀有的解决办法。 其次,我们研究过度分计制制度下的对抗性培训,即当比数据有更多的参数时。我们证明,有小扰动的对抗性培训提供了解决办法,其最小的调控点是培训数据。 山脊回归和拉伸缩非常接近这种内插式解决办法,因为它们的校正参数消失。 相比之下,对于对抗性培训而言,向内部垄断制度的过渡是突然的,非零值的扰动。 其结果用数字来说明。