City Research Online

Abstract

Rule extraction from classifiers treated as black boxes is an important topic in explainable artificial intelligence (XAI). It is concerned with finding rules that describe classifiers and that are understandable to humans, having the form of (I f...T hen...Else). Neural network classifiers are one type of classifier where it is difficult to know how the inputs map to the decision. This paper presents a technique to extract rules from a neural network where the feature space is Boolean, without looking at the inner structure of the network. For such a network with a small feature space, a Boolean function describing it can be directly calculated, whilst for a network with a larger feature space, a sampling method is described to produce rule-based approximations to the behaviour of the network with varying granularity, leading to XAI. The technique is experimentally assessed on a dataset of cross-site scripting (XSS) attacks, and proves to give very high accuracy and precision, comparable to that given by the neural network being approximated.

Publication Type:	Article
Additional Information:	Paper presented at the 11th International Joint Conference on Computational Intelligence, 17-19 Sep 2019, Vienna, Austria.
Publisher Keywords:	Neural Networks, XSS, Rule Extraction, Explainable AI
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science R Medicine > RC Internal medicine > RC0321 Neuroscience. Biological psychiatry. Neuropsychiatry
Departments:	School of Science & Technology > Computer Science
SWORD Depositor:	Symplectic Administrator

Export

Downloads