To date, the preponderance of techniques for eliciting the knowledge embedded in trained artificial neural networks (ANN's) has focused primarily on extracting rule-based explanations from feedforward ANN's. The ADT taxonomy for categorizing such techniques was proposed in 1995 to provide a basis for the systematic comparison of the different approaches. This paper shows that not only is this taxonomy applicable to a cross section of current techniques for extracting rules from trained feedforward ANN's but also how the taxonomy can be adapted and extended to embrace a broader range of ANN types (e.g., recurrent neural networks) and explanation structures. In addition the paper identifies some of the key research questions in extracting the knowledge embedded within ANN's including the need for the formulation of a consistent theoretical basis for what has been, until recently, a disparate collection of empirical results.
Abstract-Distributed Denial-of-Service (DDoS) attacks continue to be one of the most pernicious threats to the delivery of services over the Internet. Not only are DDoS attacks present in many guises, they are also continuously evolving as new vulnerabilities are exploited. Hence accurate detection of these attacks still remains a challenging problem and a necessity for ensuring high-end network security. An intrinsic challenge in addressing this problem is to effectively distinguish these Denial-of-Service attacks from similar looking Flash Events (FEs) created by legitimate clients. A considerable overlap between the general characteristics of FEs and DDoS attacks makes it difficult to precisely separate these two classes of Internet activity. In this paper we propose parameters which can be used to explicitly distinguish FEs from DDoS attacks and analyse two real-world publicly available datasets to validate our proposal. Our analysis shows that even though FEs appear very similar to DDoS attacks, there are several subtle dissimilarities which can be exploited to separate these two classes of events.
Abstract-A Flash Event (FE) represents a period of time when a web-server experiences a dramatic increase in incoming traffic, either following a newsworthy event that has prompted users to locate and access it, or as a result of redirection from other popular web or social media sites. This usually leads to network congestion and Quality-of-Service (QoS) degradation. These events can be mistaken for Distributed Denial-of-Service (DDoS) attacks aimed at disrupting the server. Accurate detection of FEs and their distinction from DDoS attacks is important, since different actions need to be undertaken by network administrators in these two cases. However, lack of public domain FE datasets hinders research in this area. In this paper we present a detailed study of flash events and classify them into three broad categories. In addition, the paper describes FEs in terms of three key components: the volume of incoming traffic, the related source IP-addresses, and the resources being accessed. We present such a FE model with minimal parameters and use publicly available datasets to analyse and validate our proposed model. The model can be used to generate different types of FE traffic, closely approximating real-world scenarios, in order to facilitate research into distinguishing FEs from DDoS attacks.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.