ALife Conference reveals bio-inspired spam detection

An algorithm for spam recognition inspired by the immune system was presented by researchers at the first European conference on Artificial Life (ALIFE XI) held in Winchester from 5-8 August 2008.

Alaa Abi-Haidar and Luis Rocha from the Department of Informatics, Indiana University, Bloomington, USA and the Instituto Gulbenkian de Ciencia, Portugal, presented a paper entitled Adaptive Spam Detection Inspired by the Immune System on Thursday 7 August. They described how in the same way as the vertebrate adaptive immune system learns to distinguish harmless from harmful substances, these principles can be applied to spam detection.

In their presentation, the authors claimed that this bio-inspired spam detection algorithm based on the cross-regulation model of T-cell dynamics, is equally as competitive as state-of-the-art spam binary classifiers and provides a deeper understanding of the behaviour of T-cell cross-regulation systems.

The newly-formed Science and Engineering of Natural Systems (SENSe) group within the University of Southampton's School of Electronics and Computer Science (ECS) is to host this year’s conference, which will take place at the University of Winchester West Downs Campus, involving 250 participants and more paper presentations than ever before.

`This is a critical time for Artificial Life,' said Dr Seth Bullock at ECS, the conference chairman. `The field is on the verge of synthesising living cells, a feat that the Artificial Life community could only dream of when it started out in the late 80s.'