Interpreting vulnerabilities of multi-instance learning to adversarial perturbations

Abstract

Multi-instance learning (MIL) is a recent machine learning paradigm which is immensely useful in various real-life applications, like image analysis, video anomaly detection, text classification, etc. It is well known that most of the existing machine learning classifiers are highly vulnerable to adversarial perturbations. Since MIL is a weakly supervised learning, where information is available for a set of instances, called bag and not for every instance, adversarial perturbations can be fatal. In this paper, we have proposed two adversarial perturbation methods to analyze the effect of adversarial perturbations to interpret the vulnerabilities of MIL methods. Out of the two algorithms, one can be customized for every bag, and the other is a universal one, which can affect all bags in a given data set and thus has some generalizability. Furthermore, through simulations, we have demonstrated the efficacy of the proposed algorithms in fooling state-of-the-art MIL approaches, such that these models make incorrect predictions regarding the label assigned to the bag. Finally, we have discussed, through experiments, about taking care of these kind of adversarial perturbations through a simple strategy. Source codes are available athttps://github.com/InkiInki/MI-UAP.