Defacement Detection with Passive Adversaries

Abstract

A novel approach to defacement detection is proposed in this paper, addressing explicitly the possible presence of a passive adversary. Defacement detection is an important security measure for Web Sites and Applications, aimed at avoiding unwanted modifications that would result in significant reputational damage. As in many other anomaly detection contexts, the algorithm used to identify possible defacements is obtained via an Adversarial Machine Learning process. We consider an exploratory setting, where the adversary can observe the detector’s alarm-generating behaviour, with the purpose of devising and injecting defacements that will pass undetected. It is then necessary to make to learning process unpredictable, so that the adversary will be unable to replicate it and predict the classifier’s behaviour. We achieve this goal by introducing a secret key—a key that our adversary does not know. The key will influence the learning process in a number of different ways, that are precisely defined in this paper. This includes the subset of examples and features that are actually used, the time of learning and testing, as well as the learning algorithm’s hyper-parameters. This learning methodology is successfully applied in this context, by using the system with both real and artificially modified Web sites. A year-long experimentation is also described, referred to the monitoring of the new Web Site of a major manufacturing company.