Abstract: Embodiments of the invention provide a method, computer program and apparatus for processing a computer message, the method comprising: upon receipt of a computer message at a computer, classifying the computer message and assigning it a message cluster identification in dependence thereon; and, utilising a message template to trans-denotate the message, wherein the message template is selected in dependence on the message cluster identification.

Abstract: A computer message that is being sent from a consumer to a computer resource is checked to determine whether the computer message meets all of a set of one or more specified conditions. If so, the computer message is compared with a baseline, the baseline containing a set of computer messages which have been classified according to whether or not each of the computer messages of the set represents acceptable behaviour in the context of the computer resource. If the comparison with the baseline determines that the computer message represents acceptable behaviour in the context of the computer resource, the computer message is permitted to be passed to the computer resource.

Abstract: A plurality of computer messages are classified into clusters according to the behaviour of the computer messages in the context of a computer resource. For a new message of the plurality of computer messages, it is determined whether the cluster to which the new computer message is classified has been seen previously. A measure is then obtained of the probability that the cluster to which the next new message will be classified has been seen previously.