Adversarial Attack Type I: Generating False Positives

False positive and false negative rates are equally important for evaluating the performance of a classifier. Adversarial examples by increasing false negative rate have been studied in recent years. However, harming a classifier by increasing false positive rate is almost blank, since it is much more difficult to generate a new and meaningful positive than the negative. To generate false positives, a supervised generative framework is proposed in this paper. Experiment results show that our method is practical and effective to generate those adversarial examples on large-scale image datasets.